WO2022181060A1 - Determination method and determination device for laser processing state - Google Patents

Determination method and determination device for laser processing state Download PDF

Info

Publication number
WO2022181060A1
WO2022181060A1 PCT/JP2022/000132 JP2022000132W WO2022181060A1 WO 2022181060 A1 WO2022181060 A1 WO 2022181060A1 JP 2022000132 W JP2022000132 W JP 2022000132W WO 2022181060 A1 WO2022181060 A1 WO 2022181060A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
light
workpiece
peak
determination
Prior art date
Application number
PCT/JP2022/000132
Other languages
French (fr)
Japanese (ja)
Inventor
和樹 藤原
浩司 船見
出 中井
Original Assignee
パナソニックＩｐマネジメント株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by パナソニックＩｐマネジメント株式会社 filed Critical パナソニックＩｐマネジメント株式会社
Priority to CN202280016159.5A priority Critical patent/CN116897090A/en
Priority to JP2023502131A priority patent/JPWO2022181060A1/ja
Publication of WO2022181060A1 publication Critical patent/WO2022181060A1/en
Priority to US18/233,954 priority patent/US20230384282A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/20—Metals
    • G01N33/207—Welded or soldered joints; Solderability
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00—Working by laser beam, e.g. welding, cutting or boring
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00—Working by laser beam, e.g. welding, cutting or boring
    • B23K26/20—Bonding
    • B23K26/21—Bonding by welding
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined

Definitions

  • the present disclosure relates to a method and apparatus for determining a processing state in laser processing for lap welding.
  • Patent Document 1 is applied to a laser welding method for welding by irradiating a laser beam generated in a pulsed form to a work, and for determining the welding state such as good/bad welding of the work, the welding state of laser welding. Discloses the determination method, etc.
  • the intensity of the plasma light and the reflected light emitted from the workpiece during laser welding is detected as the detected light intensity, and the detected light intensity corresponding to one pulse of the laser beam is preset from one cycle.
  • a pulse-by-pulse feature value is extracted for each pulse of laser light based on the detected light intensity in the extraction interval.
  • the pulse-by-pulse feature value the average value of the detected light intensity, the amount of change due to difference processing, the amplitude due to difference processing, and the like are calculated.
  • the method of Patent Document 1 obtains the lower limit value or the upper limit value of the characteristic value for each pulse as an extreme value, compares the extreme value with a predetermined threshold value, and determines the occurrence of welding defects as the welding state of each workpiece. .
  • a method for determining a processing state in laser processing for lap welding is provided. At least one of thermal radiation light, visible light, and reflected light generated at a weld formed on the surface of a workpiece by irradiating the workpiece with laser light using an optical sensor. acquiring from an optical sensor a signal indicative of a change in one of thermal radiation, visible light and reflected light in a time interval corresponding to the welding time for each workpiece; and determining the machining state.
  • the judging model is constructed based on training data including feature values calculated under conditions in which a melting shape abnormality occurs and processing states under conditions in which a melting shape abnormality occurs.
  • a processing state determination device in laser processing for lap welding includes an arithmetic circuit and a communication circuit.
  • the communication circuit uses an optical sensor to detect at least one of thermal radiation light, visible light, and reflected light generated at a weld formed on the surface of the workpiece by irradiating the workpiece with the laser beam. receive the signal generated by The signal is a signal indicative of a change in one of thermal radiation, visible light, and reflected light during a time interval corresponding to welding time for each workpiece.
  • the arithmetic circuit acquires the signal through the communication circuit, inputs the feature quantity including the signal strength of the signal based on the signal to the judgment model for judging the machining state, and determines whether there is a foreign object on the overlapping surface of the workpiece.
  • the position and number of the melt shape anomalies in the welding region having the melt length and melt width are determined as the processing state, and the determined position and number of the melt shape anomalies are output by the communication circuit as the determination result.
  • the judging model is constructed based on training data including feature values calculated under conditions in which a melting shape abnormality occurs and processing states under conditions in which a melting shape abnormality occurs.
  • FIG. 4 is a diagram for explaining signals acquired by the determination device;
  • FIG. 4 is a diagram for explaining processing for calculating a feature amount in a determination device;
  • a diagram for explaining the processing of the judgment model in the judgment device Flowchart exemplifying the training process of the judgment model A diagram for explaining a signal generated when a melt shape abnormality occurs
  • abnormalities in the molten shape such as holes in the welded part, may occur during laser irradiation.
  • the presence or absence of such abnormalities can be determined by the method of determining the occurrence of welding defects based on a threshold value, it is difficult to determine detailed processing conditions such as the number and positions of abnormalities in molten shape.
  • the present disclosure provides a determination method and determination device capable of determining in detail the processing state in laser processing for lap welding.
  • Embodiment 1 As an example of using the determination method and determination device according to the present disclosure, the component of light generated in laser processing for lap welding is detected, a signal based on the detected component is acquired, and the processing state is determined. A determination system for determining is described.
  • FIG. 1 is a diagram showing an overview of a determination system 100 according to this embodiment.
  • the determination system 100 includes a laser processing device 30 that performs laser processing for lap welding, a spectroscopic device 40 for detecting light components, and a determination device 50 .
  • the determination device 50 is an example of a determination device according to the present disclosure.
  • the workpiece 70 for lap welding is made of, for example, a metal, and when irradiated with the laser beam 6, thermal radiation light in the near-infrared region (also referred to as “thermal radiation”) and visible light, which are mainly visible light, are emitted from the metal. luminescence or plasma luminescence occurs. A part of the laser light 6 that does not contribute to processing is reflected as return light.
  • the fusion zone 27 is an example of a weld zone in this embodiment.
  • the welded region is the melted portion 27 that remains after processing on the surface of the member 70a on the side of the laser processing device 30, and includes a melted length that is the length in the direction of progress of the welding process, and a length in the direction perpendicular to the direction of progress of the welding process. is the region with the melt width, which is the width.
  • the fusion of the foreign matter 80 existing on the overlapping surfaces of the workpieces 70 also causes the fusion zone 27 to emit light.
  • the light generated in the fusion zone 27 is collected by the laser processing device 30 and transmitted to the spectroscopic device 40 through the optical fiber 13 connecting the laser processing device 30 and the spectroscopic device 40 .
  • the light transmitted to spectroscopic device 40 is separated into thermal radiation, visible light and reflected light, which are detected by optical sensor 22 of spectroscopic device 40 and converted into signals.
  • the determination device 50 of the present embodiment receives a signal from the spectroscopic device 40, it determines the position and number of abnormalities in molten shape that appear in the form of holes, etc., and the size of abnormalities in molten shape as processing conditions, Print the result.
  • FIG. 2 is a diagram illustrating the configuration of the laser processing apparatus 30 of the present embodiment.
  • a laser processing apparatus 30 includes a laser oscillator 1 , a laser transmission fiber 2 , a lens barrel 3 , a collimator lens 4 , condenser lenses 5 and 11 , a first mirror 7 and a second mirror 8 .
  • a laser oscillator 1 supplies light for generating pulsed laser light 6 with a wavelength of about 1070 nanometers (nm), for example.
  • Light supplied from a laser oscillator 1 is amplified while being transmitted by a laser transmission fiber 2, passes through a collimating lens 4 for obtaining a parallel beam, forms laser light 6, and travels through a lens barrel 3. Go straight.
  • the lens barrel 3 constitutes a processing head in the laser processing device 30 .
  • the laser beam 6 is reflected by the first mirror 7 except for a part that passes through it, is condensed by the condensing lens 5, and is fixed on, for example, a scanning table (not shown) by a jig 26 to be processed.
  • Object 70 is irradiated. Thereby, laser processing for lap welding of the workpiece 70 is performed.
  • the wavelength of the laser light 6 is not particularly limited to 1070 nm, and it is preferable to use a wavelength with a high absorption rate of the material.
  • the laser beam 6 When the laser beam 6 is irradiated, thermal radiation from the workpiece 70 , visible light due to plasma emission, and reflected light of the laser beam 6 are generated in the melting portion 27 . These lights are transmitted through the first mirror 7 , reflected by the second mirror 8 , condensed by the condensing lens 11 , and transmitted to the spectral device 40 through the optical fiber 13 . Note that the light partially transmitted through the second mirror 8 may be detected by a camera or a sensor.
  • FIG. 3 is a diagram illustrating the configuration of the spectroscopic apparatus 40 of this embodiment.
  • the spectroscopic device 40 includes a collimating lens 15, a third mirror 16, a fourth mirror 17, a fifth mirror 18, condenser lenses 19, 20 and 21, an optical sensor 22, and a A transmission cable 23 and a controller 24 are provided.
  • the housing 28 prevents miscellaneous light from entering from the outside of the spectroscopic device 40 and prevents light leakage from the inside.
  • the collimator lens 15 converts the light transmitted through the optical fiber 13 from the laser processing device 30 back into parallel light.
  • the third mirror 16 transmits visible light with a wavelength of 400 nm to 700 nm, for example, and reflects other components.
  • the fourth mirror 17 reflects the reflected light of the laser light 6 with a wavelength of about 1070 nm, for example, and transmits other components.
  • the fifth mirror 18 reflects thermal radiation with a wavelength of, for example, 1300 nm to 1550 nm.
  • the light passing through the collimator lens 15 is split into visible light, reflected light, and thermal radiation by the third mirror 16, the fourth mirror 17, and the fifth mirror 18, and condensed by the condensing lenses 19 to 21, respectively. be.
  • arbitrary band-pass filters in the optical paths after the third mirror 16, the fourth mirror 17, and the fifth mirror 18, respectively, it is possible to select the wavelength to be passed.
  • the optical sensor 22 comprises, for example, optical sensors 22a, 22b, 22c, each highly sensitive to different wavelengths.
  • the optical sensors 22a, 22b, and 22c detect visible light, reflected light, and thermal radiation condensed by the condensing lenses 19-21, respectively, and generate electrical signals corresponding to the intensity of the detected light.
  • the optical sensor 22 may be composed of one optical sensor capable of detecting the intensity for each wavelength.
  • the electrical signal generated by the optical sensor 22 is transmitted to the controller 24 via the transmission cable 23.
  • the controller 24 is a hardware controller and controls the overall operation of the spectroscopic device 40 .
  • the controller 24 includes a CPU, a communication circuit, etc., and transmits an electrical signal received from the optical sensor 22 to the determination device 50 .
  • the controller 24 has an A/D converter, for example, and converts analog electrical signals into digital signals (also simply referred to as “signals”).
  • the sampling period for conversion into a digital signal is, for example, a laser beam 6 from the viewpoint of securing a sufficient number of samples to capture the characteristics of the machining process and the tendency of local values of physical quantities in determining the machining state. is preferably 1/100 or less of the time for performing the output control.
  • FIG. 4 is a block diagram illustrating the configuration of the determination device 50 of the present embodiment.
  • the determination device 50 is configured by an information processing device such as a computer, for example.
  • the determination device 50 includes a CPU 51 that performs arithmetic processing, a communication circuit 52 that communicates with other devices, and a storage device 53 that stores data and computer programs.
  • the CPU 51 is an example of an arithmetic circuit of the determination device in this embodiment.
  • the CPU 51 implements a predetermined function including training and execution of the judgment model 57 by executing the control program 56 stored in the storage device 53 .
  • the CPU 51 executes the control program 56 so that the determination device 50 realizes the function of the determination device in the present embodiment.
  • the arithmetic circuit configured as the CPU 51 in this embodiment may be realized by various processors such as an MPU or GPU, or may be configured by one or a plurality of processors.
  • the communication circuit 52 is a communication circuit that performs communication in compliance with standards such as IEEE802.11, 4G, or 5G.
  • the communication circuit 52 may perform wired communication according to a standard such as Ethernet (registered trademark).
  • the communication circuit 52 can be connected to a communication network such as the Internet. Further, the determination device 50 may directly communicate with another device via the communication circuit 52, or may communicate via an access point. Note that the communication circuit 52 may be configured to be able to communicate with other devices without going through a communication network.
  • the communication circuit 52 may include connection terminals such as a USB (registered trademark) terminal and an HDMI (registered trademark) terminal.
  • the storage device 53 is a storage medium for storing computer programs and data necessary for realizing the functions of the determination system 100, and stores a control program 56 executed by the CPU 51 and various data.
  • the storage device 53 stores the judgment model 57 after the judgment model 57 is constructed.
  • the judgment model 57 is constructed based on training data including the feature amount calculated from the signal under the condition where the melting shape anomaly occurs and the processing state when the melting shape anomaly occurs. The details of the judgment model 57 will be described later.
  • the storage device 53 is composed of, for example, a magnetic storage device such as a hard disk drive (HDD), an optical storage device such as an optical disk drive, or a semiconductor storage device such as an SSD.
  • the storage device 53 may include a temporary storage element configured by RAM such as DRAM or SRAM, and may function as an internal memory of the CPU 51 .
  • the determination system 100 configured as described above, for example, as shown in FIG. Detect light.
  • the spectroscopic device 40 transmits to the determination device 50 a signal corresponding to the intensity of the detected thermal radiation, visible light and reflected light.
  • the operation of the determination device 50 in this system 100 will be described below.
  • FIG. 5 is a flowchart illustrating determination processing in the determination device 50 of this embodiment. Each process shown in this flowchart is executed by the CPU 51 of the determination device 50, for example. This flowchart is started, for example, when the user of the determination system 100 or the like inputs a predetermined operation for starting determination processing from an input device connected via the communication circuit 52 .
  • the CPU 51 acquires signals corresponding to thermal radiation, visible light, and reflected light detected by the optical sensor 22 of the spectroscopic device 40 through the communication circuit 52 (S1).
  • FIG. 6 is a diagram for explaining signals acquired by the determination device 50.
  • FIG. (A) of FIG. 6 illustrates signal waveforms of signals corresponding to any one of thermal radiation, visible light, and reflected light when a melting shape abnormality occurs during processing.
  • (B) of FIG. 6 illustrates signal waveforms of any one of thermal radiation, visible light, and reflected light when no melt shape abnormality occurs.
  • (C) of FIG. 6 shows the output of the laser beam 6 with which the workpiece 70 is irradiated.
  • the signals of FIGS. 6A and 6B correspond to either thermal radiation, visible light, or reflected light generated by the laser output of FIG. 6C.
  • the horizontal axis indicates time
  • the vertical axis indicates signal intensity ((A) and (B) in FIG. 6) or laser output ((C) in FIG. 6).
  • time T1 indicates a time interval corresponding to one pulse of the laser light 6
  • time T2 indicates a time interval of peak output excluding rise and fall of the laser output.
  • welding for each workpiece 70 is performed at time T1.
  • the CPU 51 acquires signals indicating changes in heat radiation, visible light, and reflected light at time T1 corresponding to the welding time for each workpiece 70.
  • a waveform signal having a peak in which the signal intensity temporarily increases compared to the normal state shown in (B) of FIG. 6 is obtained.
  • a signal peak at the time of occurrence of a melting shape anomaly is caused by, for example, light emission by the foreign matter 80 that causes the anomaly. It should be noted that when the melt shape abnormality occurs, the light emission is momentarily attenuated by the foreign matter 80, and an attenuation peak may occur temporarily. In this case, a signal having a waveform with a temporarily decreasing peak is obtained.
  • the integrated value can be calculated by extracting the local minimum value and subtracting the average value Sa from the signal intensity in the section Tp, in the flow shown in the flowchart of FIG. 5, which will be described later.
  • the flow will be described for a signal having a waveform when a peak in which the signal intensity increases temporarily occurs.
  • the CPU 51 next calculates the feature amount to be input to the determination model 57 from the acquired signal (S2).
  • the CPU 51 calculates an intensity value based on the signal intensity at the peak (hereinafter referred to as "peak intensity value") in addition to the signal intensity to which preprocessing such as normalization is applied, as the feature quantity.
  • FIG. 7 is a diagram for explaining the processing (S2) for calculating the feature amount in the determination device 50.
  • FIG. FIG. 7(A) like FIG. 6(A), shows changes over time in the signal intensity of the signal corresponding to thermal radiation, visible light, or reflected light when a melt shape abnormality occurs. Processing for calculating the feature amount of the peak intensity value in step S2 of FIG. 5 will be described with reference to FIG.
  • the CPU 51 first performs processing to detect the peak of the acquired signal.
  • the CPU 51 for example, performs an operation to compare the signal strength values for each sampling period, and extracts a point having a larger value than the temporally adjacent points before and after as a local maximum value.
  • a threshold value may be set from the viewpoint of limiting the value extracted as the local maximum value to a predetermined signal strength or more.
  • the CPU 51 for example, extracts the local minimum value of the signal intensity in the same manner as the local maximum value, and extracts the peak to detect Interval Tp corresponds to the peak occurrence time.
  • (B) of FIG. 7 shows an example in which the peak of section Tp is detected in the signal of (A) of FIG.
  • the CPU 51 calculates the average value Sa of the signal intensity excluding the peak.
  • the average value Sa is calculated, for example, as an average value of signal intensities at a time (T2 ⁇ Tp) excluding the section Tp from the time T2 of the peak output in one pulse of the laser beam 6 .
  • (C) of FIG. 7 shows an example of calculating the average value Sa in the example of (B) of FIG.
  • the CPU 51 calculates, as a peak intensity value, the integrated value calculated for the section Tp corresponding to the peak occurrence time, with the value obtained by subtracting the average value Sa of the signal strength excluding the peak from the signal strength of the section Tp. .
  • (D) of FIG. 7 shows an example of calculating the integral value in the example of (C) of FIG. 7 .
  • the integrated value corresponds to the area of the region Rp shown in (D) of FIG.
  • the CPU 51 After calculating the feature amount as described above (S2), the CPU 51 inputs the feature amount to the determination model 57 and performs determination model processing (S3) for determining the position, number, and size of the molten shape abnormality.
  • the feature quantity of the signal intensity is input to the determination model 57 as, for example, the amplitude of the signal waveform for each sampling period in A/D conversion.
  • FIG. 8 is a diagram for explaining the judgment model processing (S3).
  • FIG. 8(A) shows a signal waveform when a melting shape abnormality occurs as in FIG. 6(A).
  • (B) of FIG. 8 schematically shows the appearance of a member 70a of the workpiece 70 on the side of the laser processing apparatus 30 after processing when the signal of (A) of FIG. 8 is generated.
  • a hole 85 is generated as an example of a melt shape abnormality in a weld region 270 having a melt length Wx and a melt width Wy.
  • the laser processing apparatus 30 of this embodiment performs welding over the fusion length Wx for each workpiece 70 in the time T1 corresponding to one pulse.
  • the peak of the section Tp corresponds to the occurrence of the hole 85 when the laser processing apparatus 30 advances the processing in the positive direction of the x-axis in (B) of FIG. arises and is detected in step S2.
  • the CPU 51 inputs the feature amounts of the signal intensity and the peak intensity value calculated from the signal of FIG. Determine location, number and size of holes 85 in (B).
  • the position is determined, for example, as the coordinates of the center of gravity of the hole 85 in an orthogonal coordinate system whose origin is the welding start point on the member 70a.
  • the size is determined as the area of the hole 85, for example. The number is determined to be "1" in FIG.
  • the CPU 51 outputs the determination result of the position, number and size of the abnormal shape of the melt such as the hole 85 through the communication circuit 52 (S4).
  • the determination result can be received and displayed by, for example, an external information processing device or display device.
  • the determination device 50 may be provided with a display device (for example, a display) that can communicate with the CPU 51, and the determination result may be displayed on the display device.
  • the flowchart of FIG. 5 is repeatedly executed, for example, every time welding is performed for each workpiece 70 .
  • the determination device 50 of the present embodiment acquires the signal generated by the optical sensor 22 of the spectroscopic device 40 (S1), calculates the feature amount from the signal (S2), and calculates the feature amount (S3). Thereby, the determination device 50 can determine in detail the processing state related to the melt shape abnormality in laser processing for lap welding.
  • the feature amount may be calculated for all of thermal radiation, visible light, and reflected light, or may be calculated for any one of thermal radiation, visible light, and reflected light.
  • the judgment model 57 may judge only the position and number of melt shape abnormalities, for example.
  • the above-described attenuation peak may also be detected to calculate the integrated value of the signal intensity.
  • the value for the attenuation peak will be negative, while the peak intensity value calculated for the increase peak described in the example of FIG. 7 will be positive. In this way, it is possible to distinguish between peaks due to attenuation and peaks due to increase in signal intensity, and to reflect changes in light emission due to the foreign matter 80 in the feature amount.
  • the integrated value of the signal intensity for the peak is not limited to this, and for example, focusing only on the presence and size of the peak, the absolute value is used as the feature amount.
  • FIG. 9 is a flowchart illustrating training processing of the judgment model 57.
  • FIG. Each process of this flowchart is executed by the CPU 51 of the determination device 50, for example.
  • the CPU 51 acquires training data stored in advance, for example, in the storage device 53 (S11).
  • the training data is data that associates the feature values such as the signal intensity and peak intensity value of thermal radiation, visible light, and reflected light with the position, number, and size of molten shape anomalies as processing conditions.
  • the training data includes feature values calculated from signals based on thermal radiation, visible light, and reflected light detected by laser processing under a plurality of conditions in which the processing state changes, and the appearance measurement of the welded region 270 after processing. It is constructed by recording in association with the machining state determined by. Appearance measurement can be performed, for example, by observing the welded region 270 with an optical microscope or by measuring an image of the welded region 270, but is not limited to this.
  • FIG. 10 is a diagram for explaining signals generated when a melt shape abnormality occurs.
  • features based on signals having various waveform patterns as illustrated in FIG. 10 and corresponding machining states are collected.
  • a peak corresponding to one melt shape anomaly is detected in all of the signals Lt, Lv, and Lr generated according to the intensity of thermal radiation, visible light, and reflected light, respectively.
  • one melting shape anomaly peak is detected in the two signals Lt and Lv of thermal radiation and visible light.
  • one melting shape abnormality peak is detected only in the reflected light signal Lr.
  • two peaks corresponding to two melting shape anomalies are detected in each of the thermal radiation, visible light, and reflected light signals Lt, Lv, and Lr. As shown in FIGS. 10A and 10D, the reflected light signal Lr tends to peak at earlier times than the thermal radiation and visible light signals Lt and Lv.
  • the conditions such as light, time, and number of peaks detected by the processing described later can be changed.
  • peaks are detected only in one or two signals of thermal radiation, visible light, and reflected light.
  • the judgment model 57 can reflect the tendency of the melt shape abnormality to occur.
  • data containing two or less peaks is used as the number of peaks assumed during actual processing, but data containing three or more peaks may also be used.
  • a time interval regarded as one peak may be set in advance.
  • the CPU 51 When the CPU 51 acquires the training data (S1), it performs machine learning using the training data to generate the judgment model 57 (S2).
  • the judgment model 57 is generated as a regression model based on, for example, random forest or neural network.
  • the position, number, and size of the abnormal shape of the melt can be determined as a learned model. 57 can be generated.
  • the training process for the determination model 57 may be executed in an information processing device different from the determination device 50 .
  • the determination device 50 may acquire the built determination model by the communication circuit 52, for example, via a communication network.
  • the training data for the determination model 57 may include the feature amount when no melting shape anomaly has occurred and the processing state when no melting shape anomaly has occurred.
  • the feature value when no melting shape abnormality has occurred may be a peak intensity value of “0”.
  • a processing state in which no melt shape anomaly has occurred may be, for example, a position of '0', a number of melt shape anomalies of '0', and a size of '0'.
  • the determination processing provides a method for determining the processing state in laser processing for lap welding.
  • This method uses the optical sensor 22 to detect heat radiation ( A step of detecting at least one of thermal radiation light), visible light and reflected light, and changes in the thermal radiation, visible light and reflected light at time T1 (time interval) corresponding to the welding time for each workpiece 70
  • Steps (S2, S3) for determining, as a processing state, the position and number of the abnormal molten shape in the welding region 270 having the molten length Wx and the molten width Wy of the abnormal molten shape that occurs when the foreign matter 80 is present
  • the determination model 57 uses the optical sensor 22 to detect heat radiation ( A step of detecting at
  • a signal based on one or more of thermal radiation, visible light, and reflected light generated and detected by the irradiation of the laser beam 6 is acquired (S1), and the feature amount including the signal intensity is calculated. Then, the position and number of melt shape abnormalities are determined as the processing state (S2, S3). Accordingly, it is possible to determine in detail the processing state related to the melt shape abnormality based on the signal intensity of at least one of thermal radiation, visible light, and reflected light detected in laser processing for lap welding.
  • the determination steps (S2, S3) include detecting the peak of the signal and determining the size of the melt shape abnormality as the processing state.
  • the step of outputting (S4) further includes outputting the determined size of the melt shape abnormality as a determination result.
  • the feature quantity includes a peak intensity value, which is an example of an intensity value based on the signal intensity of the signal at the peak.
  • the intensity value is an integrated value obtained by subtracting the average value Sa of the signal intensity of the signal excluding the peak from the signal intensity of the peak, and integrating it over the interval Tp (peak occurrence time). (see FIG. 7).
  • the determination model 57 is a signal based on at least one of thermal radiation, visible light, and reflected light detected by performing laser processing under each of a plurality of conditions in which the processing state changes. and the machined state determined by the appearance measurement of the welding region 270 are associated with each other.
  • a determination model 57 for determining the machining state is obtained from feature amounts based on at least one of thermal radiation, visible light, and reflected light.
  • the determination device 50 is an example of a processing state determination device in laser processing for lap welding.
  • the determination device 50 includes a CPU 51 as an example of an arithmetic circuit and a communication circuit 52 .
  • the communication circuit 52 transmits thermal radiation (thermal radiation light) generated in a melted portion 27 (an example of a welded portion) formed on the surface of the workpiece 70 by irradiating the workpiece 70 with the laser beam 6.
  • a signal generated by detecting at least one of light and reflected light by the optical sensor 22 is received.
  • the signal is a signal that indicates changes in at least one of thermal radiation, visible light, and reflected light at time T1 as an example of a time interval corresponding to welding time for each workpiece 70 .
  • the CPU 51 acquires the signal through the communication circuit 52 (S1), inputs the feature amount including the signal strength of the signal based on the signal to the judgment model 57 for judging the machining state, and makes the overlapped surface of the workpiece 70.
  • the position and number of the melt shape anomalies in the welding region 270 having the melt length Wx and the melt width Wy, which occur when the foreign matter 80 is present, are determined as the processing state (S2, S3), and the determined melt shape anomalies are determined. and the number as a determination result are output by the communication circuit 52 (S4).
  • the determination model 57 is constructed based on training data including feature values calculated under conditions in which abnormalities in the molten shape occur and processing states in conditions in which the abnormalities in the molten shape occur.
  • the determination device 50 described above it is possible to perform the determination method described above and determine the processing state in laser processing for lap welding in detail.
  • the determination device 50 calculated the feature amounts of the signal intensity and the peak intensity value in the determination process (S2 in FIG. 5). In this embodiment, in step S2, only the signal intensity may be used as the feature amount without calculating the peak intensity value.
  • the determination device 50 acquires signals corresponding to thermal radiation, visible light, and reflected light detected by the optical sensor 22 of the spectroscopic device 40 (S1).
  • the determination device 50 may acquire signals for only one or two of thermal radiation, visible light and reflected light.
  • step S 2 and S 3 feature quantities are calculated for only one or two signals of thermal radiation, visible light, and reflected light, and input to the determination model 57 .
  • the judgment model 57 may be constructed using feature amounts and processing states based on signals of only one or two of thermal radiation, visible light, and reflected light as training data.
  • the judgment model 57 is constructed using feature quantities such as signal intensity and the positions, numbers, and sizes of molten shape anomalies as training data (S11-S12).
  • the judgment model 57 may be constructed using the feature quantity and the positions and numbers of the abnormalities in the molten shape as training data.
  • the determination device 50 determines the position and number of melt shape abnormalities as the processing state in the determination processing (S1 to S4).
  • the processing state in laser processing for lap welding, the processing state can be determined in detail, particularly with regard to the melt shape abnormality that has occurred in the welding region.
  • the present disclosure is applicable to a processing state determination system in laser processing for lap welding, and is particularly applicable to a method and apparatus for determining molten shape anomalies in welds.

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Immunology (AREA)
  • General Physics & Mathematics (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Optics & Photonics (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Mechanical Engineering (AREA)
  • Plasma & Fusion (AREA)
  • Laser Beam Processing (AREA)

Abstract

This determination method for a processing state comprises: a step for detecting, using an optical sensor, at least one of heat radiating light, visible light, and reflected light that generate in a welding portion formed on the surface of a workpiece due to the workpiece being irradiated with laser light; a step for acquiring, from the optical sensor, a signal indicating a change in one of heat radiation, visible light, and reflected light in a time period corresponding to a welding time for each workpiece; a step in which a feature amount including a signal intensity of a signal is input into a determination model for determining a processing state and then the positions and number of abnormal shaped welds within a welding area with a melted length and a melted width are determined as the processing state, the abnormal shaped welds occurring when a foreign substance is present between the overlapping surfaces in the workpiece; and a step for outputting the determination result. The determination model is established on the basis of training data including: feature amounts calculated under the condition that abnormal shaped welds are occurring; and processing states under the condition that abnormal shaped welds are occurring.

Description

レーザ加工状態の判定方法及び判定装置Determination method and determination device for laser processing state
　本開示は、重ね合わせ溶接のためのレーザ加工における加工状態の判定方法、及び判定装置に関する。 The present disclosure relates to a method and apparatus for determining a processing state in laser processing for lap welding.
　特許文献１は、パルス状に発生するレーザ光をワークに照射して溶接を行うレーザ溶接方法に適用され、ワークにおける溶接の良／不良等の溶接状態を判定するための、レーザ溶接の溶接状態判定方法等を開示している。特許文献１の方法は、レーザ溶接時にワークから放出されるプラズマ光および反射光の強度を検出光強度として検出し、レーザ光の１パルスに対応する検出光強度の１周期のうちから予め設定した抽出区間における検出光強度に基づいてパルス毎特徴値をレーザ光のパルス毎に抽出する。パルス毎特徴値として、検出光強度の平均値、差分処理による変化量、および差分処理による振幅などが算出される。特許文献１の方法は、パルス毎特徴値の下限値または上限値を極値として得て、極値と所定のしきい値とを比較し、ワーク毎の溶接状態として溶接欠陥の発生を判定する。 Patent Document 1 is applied to a laser welding method for welding by irradiating a laser beam generated in a pulsed form to a work, and for determining the welding state such as good/bad welding of the work, the welding state of laser welding. Discloses the determination method, etc. In the method of Patent Document 1, the intensity of the plasma light and the reflected light emitted from the workpiece during laser welding is detected as the detected light intensity, and the detected light intensity corresponding to one pulse of the laser beam is preset from one cycle. A pulse-by-pulse feature value is extracted for each pulse of laser light based on the detected light intensity in the extraction interval. As the pulse-by-pulse feature value, the average value of the detected light intensity, the amount of change due to difference processing, the amplitude due to difference processing, and the like are calculated. The method of Patent Document 1 obtains the lower limit value or the upper limit value of the characteristic value for each pulse as an extreme value, compares the extreme value with a predetermined threshold value, and determines the occurrence of welding defects as the welding state of each workpiece. .
特開２０００－１５３３７９号公報JP-A-2000-153379
　本開示の一態様によると、重ね合わせ溶接のためのレーザ加工における加工状態の判定方法が提供される。本方法は、光センサを用いて、レーザ光が被加工物に照射されることで被加工物の表面に形成される溶接部において発生する熱放射光、可視光及び反射光のうち、少なくとも１つを検出する工程と、被加工物ごとの溶接時間に対応した時間区間における熱放射、可視光及び反射光のうち１つの変化を示す信号を光センサから取得する工程と、加工状態を判定する判定モデルに信号に基づく信号の信号強度を含む特徴量を入力して、被加工物の重ね合わせ面に異物が存在する場合に生じる溶融形状異常の、溶融長と溶融幅を有する溶接領域における位置及び数を、加工状態として、判定する工程と、判定した溶融形状異常の位置及び数を判定結果として出力する工程とを含む。判定モデルは、溶融形状異常が発生している状況下で算出された特徴量と溶融形状異常が発生している状況下での加工状態とを含む訓練データに基づいて構築される。 According to one aspect of the present disclosure, a method for determining a processing state in laser processing for lap welding is provided. At least one of thermal radiation light, visible light, and reflected light generated at a weld formed on the surface of a workpiece by irradiating the workpiece with laser light using an optical sensor. acquiring from an optical sensor a signal indicative of a change in one of thermal radiation, visible light and reflected light in a time interval corresponding to the welding time for each workpiece; and determining the machining state. By inputting the feature value including the signal strength of the signal based on the signal into the judgment model, the position of the welding area having the fusion length and the fusion width of the fusion shape abnormality that occurs when there is a foreign matter on the overlapping surface of the workpiece and number as the processing state, and a step of outputting the determined position and number of the melt shape abnormality as a determination result. The judging model is constructed based on training data including feature values calculated under conditions in which a melting shape abnormality occurs and processing states under conditions in which a melting shape abnormality occurs.
　本開示の一態様によると、重ね合わせ溶接のためのレーザ加工における加工状態の判定装置が提供される。判定装置は、演算回路と、通信回路とを備える。通信回路は、レーザ光が被加工物に照射されることで被加工物の表面に形成される溶接部において発生する熱放射光、可視光及び反射光のうち、少なくとも１つを光センサにより検出して生成された信号を受け付ける。信号は、被加工物ごとの溶接時間に対応した時間区間における熱放射、可視光及び反射光のうち１つの変化を示す信号である。演算回路は、通信回路により、信号を取得し、加工状態を判定する判定モデルに信号に基づく信号の信号強度を含む特徴量を入力して、被加工物の重ね合わせ面に異物が存在する場合に生じる溶融形状異常の、溶融長と溶融幅を有する溶接領域における位置及び数を、加工状態として、判定し、判定した溶融形状異常の位置及び数を判定結果として、通信回路により出力する。判定モデルは、溶融形状異常が発生している状況下で算出された特徴量と溶融形状異常が発生している状況下での加工状態とを含む訓練データに基づいて構築される。 According to one aspect of the present disclosure, a processing state determination device in laser processing for lap welding is provided. The determination device includes an arithmetic circuit and a communication circuit. The communication circuit uses an optical sensor to detect at least one of thermal radiation light, visible light, and reflected light generated at a weld formed on the surface of the workpiece by irradiating the workpiece with the laser beam. receive the signal generated by The signal is a signal indicative of a change in one of thermal radiation, visible light, and reflected light during a time interval corresponding to welding time for each workpiece. The arithmetic circuit acquires the signal through the communication circuit, inputs the feature quantity including the signal strength of the signal based on the signal to the judgment model for judging the machining state, and determines whether there is a foreign object on the overlapping surface of the workpiece. The position and number of the melt shape anomalies in the welding region having the melt length and melt width are determined as the processing state, and the determined position and number of the melt shape anomalies are output by the communication circuit as the determination result. The judging model is constructed based on training data including feature values calculated under conditions in which a melting shape abnormality occurs and processing states under conditions in which a melting shape abnormality occurs.
本開示の実施形態１に係る判定システムの概要を示す図A diagram showing an overview of a determination system according to Embodiment 1 of the present disclosure 判定システムにおけるレーザ加工装置の構成を例示する図The figure which illustrates the structure of the laser processing apparatus in a determination system 判定システムにおける分光装置の構成を例示する図The figure which illustrates the structure of the spectrometer in a determination system. 判定システムにおける判定装置の構成を例示するブロック図Block diagram illustrating the configuration of a determination device in the determination system 判定装置における判定処理を例示するフローチャートFlowchart illustrating determination processing in determination device 判定装置において取得される信号を説明するための図FIG. 4 is a diagram for explaining signals acquired by the determination device; 判定装置において特徴量を算出する処理を説明するための図FIG. 4 is a diagram for explaining processing for calculating a feature amount in a determination device; 判定装置における判定モデルの処理を説明するための図A diagram for explaining the processing of the judgment model in the judgment device 判定モデルの訓練処理を例示するフローチャートFlowchart exemplifying the training process of the judgment model 溶融形状異常の発生時において生成される信号を説明するための図A diagram for explaining a signal generated when a melt shape abnormality occurs
　レーザ溶接において、例えば被加工物に汚れ或いは異物が存在した場合、レーザ照射時に、溶接部に穴が空くといった溶融形状の異常を生じることがある。しきい値により溶接欠陥の発生を判定する方法では、こうした異常の有無については判断し得るが、溶融形状異常の数及び位置等の詳細な加工状態まで判定することは困難であった。 In laser welding, for example, if there is dirt or foreign matter on the workpiece, abnormalities in the molten shape, such as holes in the welded part, may occur during laser irradiation. Although the presence or absence of such abnormalities can be determined by the method of determining the occurrence of welding defects based on a threshold value, it is difficult to determine detailed processing conditions such as the number and positions of abnormalities in molten shape.
　本開示は、重ね合わせ溶接のためのレーザ加工における加工状態を詳細に判定することができる判定方法及び判定装置を提供する。 The present disclosure provides a determination method and determination device capable of determining in detail the processing state in laser processing for lap welding.
　以下、適宜図面を参照しながら、実施の形態を詳細に説明する。但し、必要以上に詳細な説明は省略する場合がある。例えば、既によく知られた事項の詳細説明や実質的に同一の構成に対する重複説明を省略する場合がある。これは、以下の説明が不必要に冗長になるのを避け、当業者の理解を容易にするためである。なお、発明者は、当業者が本開示を十分に理解するために添付図面および以下の説明を提供するのであって、これらによって特許請求の範囲に記載の主題は限定されることはない。 Hereinafter, embodiments will be described in detail with reference to the drawings as appropriate. However, more detailed description than necessary may be omitted. For example, detailed descriptions of well-known matters and redundant descriptions of substantially the same configurations may be omitted. This is to avoid unnecessary verbosity in the following description and to facilitate understanding by those skilled in the art. It should be noted that the inventors provide the accompanying drawings and the following description for a full understanding of the present disclosure by those skilled in the art, and not for limiting the claimed subject matter.
　（実施形態１）
　実施形態１では、本開示に係る判定方法及び判定装置を用いる一例として、重ね合わせ溶接のためのレーザ加工において発生する光の成分を検出し、検出した成分に基づく信号を取得して、加工状態を判定する判定システムについて説明する。 (Embodiment 1)
In Embodiment 1, as an example of using the determination method and determination device according to the present disclosure, the component of light generated in laser processing for lap welding is detected, a signal based on the detected component is acquired, and the processing state is determined. A determination system for determining is described.
　１．構成
　実施形態１に係る判定システムについて、図１を用いて説明する。図１は、本実施形態に係る判定システム１００の概要を示す図である。 1. Configuration A determination system according to Embodiment 1 will be described with reference to FIG. FIG. 1 is a diagram showing an overview of a determination system 100 according to this embodiment.
　１－１．システムの概要
　判定システム１００は、重ね合わせ溶接のためのレーザ加工を行うレーザ加工装置３０と、光の成分を検出するための分光装置４０と、判定装置５０とを備える。判定装置５０は、本開示に係る判定装置の一例である。重ね合わせ溶接の被加工物７０は例えば金属からなり、レーザ光６が照射されると温度上昇による近赤外線領域の熱放射光（「熱放射」ともいう）、及び主に可視光である金属固有の発光またはプラズマ発光が発生する。また、レーザ光６は、加工に寄与しない一部が戻り光として反射する。このように、レーザ加工装置３０から、レーザ光６が被加工物７０に照射されると、被加工物７０に形成される溶融部２７において、熱放射、可視光及び反射光が発生する。溶融部２７は、本実施形態における溶接部の一例である。 1-1. Overview of System The determination system 100 includes a laser processing device 30 that performs laser processing for lap welding, a spectroscopic device 40 for detecting light components, and a determination device 50 . The determination device 50 is an example of a determination device according to the present disclosure. The workpiece 70 for lap welding is made of, for example, a metal, and when irradiated with the laser beam 6, thermal radiation light in the near-infrared region (also referred to as “thermal radiation”) and visible light, which are mainly visible light, are emitted from the metal. luminescence or plasma luminescence occurs. A part of the laser light 6 that does not contribute to processing is reflected as return light. As described above, when the laser beam 6 is irradiated from the laser processing apparatus 30 to the workpiece 70 , thermal radiation, visible light and reflected light are generated in the melted portion 27 formed in the workpiece 70 . The fusion zone 27 is an example of a weld zone in this embodiment.
　レーザ光６が照射された際、例えば被加工物７０を構成する２つの部材７０ａ、７０ｂの間に、樹脂またはオイル等の炭素系材料からなる異物８０が存在すると、溶接領域に穴が空いたり、突起を形成したりする溶融形状異常が生じる。溶接領域は、レーザ加工装置３０側の部材７０ａの表面において、加工後に溶融部２７の跡として残り、溶接加工の進行方向にわたる長さである溶融長と、溶接加工の進行方向と垂直な方向の幅である溶融幅とを有する領域である。こうした被加工物７０の重ね合わせ面に存在する異物８０の溶融によっても、溶融部２７において発光が生じる。 When the laser beam 6 is irradiated, for example, if there is a foreign matter 80 made of a carbonaceous material such as resin or oil between the two members 70a and 70b that constitute the workpiece 70, a hole will be formed in the welding area. , a melting shape anomaly such as the formation of protrusions occurs. The welded region is the melted portion 27 that remains after processing on the surface of the member 70a on the side of the laser processing device 30, and includes a melted length that is the length in the direction of progress of the welding process, and a length in the direction perpendicular to the direction of progress of the welding process. is the region with the melt width, which is the width. The fusion of the foreign matter 80 existing on the overlapping surfaces of the workpieces 70 also causes the fusion zone 27 to emit light.
　溶融部２７において発生した光は、レーザ加工装置３０において集光され、レーザ加工装置３０と分光装置４０を接続する光ファイバ１３を通して、分光装置４０に伝送される。分光装置４０に伝送された光は、熱放射、可視光及び反射光に分光され、分光装置４０の光センサ２２により検知されて、信号に変換される。本実施形態の判定装置５０は、分光装置４０から信号を受信すると、加工状態として、穴あき等の形態において発現する溶融形状異常の位置及び数、さらに溶融形状異常のサイズを判定して、判定結果を出力する。 The light generated in the fusion zone 27 is collected by the laser processing device 30 and transmitted to the spectroscopic device 40 through the optical fiber 13 connecting the laser processing device 30 and the spectroscopic device 40 . The light transmitted to spectroscopic device 40 is separated into thermal radiation, visible light and reflected light, which are detected by optical sensor 22 of spectroscopic device 40 and converted into signals. When the determination device 50 of the present embodiment receives a signal from the spectroscopic device 40, it determines the position and number of abnormalities in molten shape that appear in the form of holes, etc., and the size of abnormalities in molten shape as processing conditions, Print the result.
　１－２．レーザ加工装置の構成
　図２は、本実施形態のレーザ加工装置３０の構成を例示する図である。レーザ加工装置３０は、レーザ発振器１と、レーザ伝送用ファイバ２と、鏡筒３と、コリメートレンズ４と、集光レンズ５、１１と、第１ミラー７と、第２ミラー８とを備える。 1-2. Configuration of Laser Processing Apparatus FIG. 2 is a diagram illustrating the configuration of the laser processing apparatus 30 of the present embodiment. A laser processing apparatus 30 includes a laser oscillator 1 , a laser transmission fiber 2 , a lens barrel 3 , a collimator lens 4 , condenser lenses 5 and 11 , a first mirror 7 and a second mirror 8 .
　レーザ発振器１は、例えば波長が約１０７０ナノメートル（ｎｍ）のパルス状のレーザ光６を発生するための光を供給する。レーザ発振器１から供給された光は、レーザ伝送用ファイバ２により伝送される間に増幅され、平行なビームを得るためのコリメートレンズ４を通り、レーザ光６を形成して、鏡筒３内を直進する。鏡筒３は、レーザ加工装置３０における加工ヘッドを構成する。 A laser oscillator 1 supplies light for generating pulsed laser light 6 with a wavelength of about 1070 nanometers (nm), for example. Light supplied from a laser oscillator 1 is amplified while being transmitted by a laser transmission fiber 2, passes through a collimating lens 4 for obtaining a parallel beam, forms laser light 6, and travels through a lens barrel 3. Go straight. The lens barrel 3 constitutes a processing head in the laser processing device 30 .
　レーザ光６は、第１ミラー７において透過する一部を除いて反射し、集光レンズ５により集光されて、例えば走査テーブル（図示せず）上に押さえ治具２６で固定された被加工物７０に照射される。これにより、被加工物７０の重ね合わせ溶接のためのレーザ加工が行われる。なお、レーザ光６の波長は特に１０７０ｎｍに限らず、材料の吸収率が高い波長を用いることが好ましい。 The laser beam 6 is reflected by the first mirror 7 except for a part that passes through it, is condensed by the condensing lens 5, and is fixed on, for example, a scanning table (not shown) by a jig 26 to be processed. Object 70 is irradiated. Thereby, laser processing for lap welding of the workpiece 70 is performed. The wavelength of the laser light 6 is not particularly limited to 1070 nm, and it is preferable to use a wavelength with a high absorption rate of the material.
　レーザ光６が照射されると、溶融部２７において被加工物７０からの熱放射、プラズマ発光による可視光、及びレーザ光６の反射光が発生する。これらの光は、第１ミラー７を透過し、第２ミラー８で反射して、集光レンズ１１により集光された後、光ファイバ１３を通って分光装置４０に伝送される。なお、第２ミラー８において一部透過する光をカメラまたはセンサにより検知してもよい。 When the laser beam 6 is irradiated, thermal radiation from the workpiece 70 , visible light due to plasma emission, and reflected light of the laser beam 6 are generated in the melting portion 27 . These lights are transmitted through the first mirror 7 , reflected by the second mirror 8 , condensed by the condensing lens 11 , and transmitted to the spectral device 40 through the optical fiber 13 . Note that the light partially transmitted through the second mirror 8 may be detected by a camera or a sensor.
　１－３．分光装置の構成
　図３は、本実施形態の分光装置４０の構成を例示する図である。分光装置４０は、筐体２８の内部に、コリメートレンズ１５と、第３ミラー１６と、第４ミラー１７と、第５ミラー１８と、集光レンズ１９、２０、２１と、光センサ２２と、伝送ケーブル２３と、コントローラ２４とを備える。筐体２８は、分光装置４０の外部から雑光が内部に入ることを防ぎ、内部からの光漏れを防止する。 1-3. Configuration of Spectroscopic Apparatus FIG. 3 is a diagram illustrating the configuration of the spectroscopic apparatus 40 of this embodiment. The spectroscopic device 40 includes a collimating lens 15, a third mirror 16, a fourth mirror 17, a fifth mirror 18, condenser lenses 19, 20 and 21, an optical sensor 22, and a A transmission cable 23 and a controller 24 are provided. The housing 28 prevents miscellaneous light from entering from the outside of the spectroscopic device 40 and prevents light leakage from the inside.
　コリメートレンズ１５は、レーザ加工装置３０から光ファイバ１３を通して伝送された光を平行光に戻す。第３ミラー１６は、例えば波長が４００ｎｍ～７００ｎｍの可視光を透過し、それ以外の成分を反射する。第４ミラー１７は、例えば波長が約１０７０ｎｍのレーザ光６の反射光を反射し、それ以外の成分を透過する。第５ミラー１８は、例えば波長が１３００ｎｍ～１５５０ｎｍの熱放射を反射する。 The collimator lens 15 converts the light transmitted through the optical fiber 13 from the laser processing device 30 back into parallel light. The third mirror 16 transmits visible light with a wavelength of 400 nm to 700 nm, for example, and reflects other components. The fourth mirror 17 reflects the reflected light of the laser light 6 with a wavelength of about 1070 nm, for example, and transmits other components. The fifth mirror 18 reflects thermal radiation with a wavelength of, for example, 1300 nm to 1550 nm.
　コリメートレンズ１５を通った光は、第３ミラー１６、第４ミラー１７、及び第５ミラー１８により、可視光、反射光、及び熱放射に分光され、それぞれ集光レンズ１９～２１により集光される。なお、第３ミラー１６、第４ミラー１７、及び第５ミラー１８の後の光路に、それぞれ任意の帯域通過フィルタを配置することで、通過させる波長を選択可能としてもよい。 The light passing through the collimator lens 15 is split into visible light, reflected light, and thermal radiation by the third mirror 16, the fourth mirror 17, and the fifth mirror 18, and condensed by the condensing lenses 19 to 21, respectively. be. In addition, by arranging arbitrary band-pass filters in the optical paths after the third mirror 16, the fourth mirror 17, and the fifth mirror 18, respectively, it is possible to select the wavelength to be passed.
　光センサ２２は、例えば各々が異なる波長に高い感度を有する光センサ２２ａ、２２ｂ、２２ｃを備える。光センサ２２ａ、２２ｂ、２２ｃは、それぞれ各集光レンズ１９～２１により集光された可視光、反射光、及び熱放射を検出して、検出した光の強度に応じた電気信号を生成する。なお、光センサ２２は、波長ごとの強度を検出可能な１つの光センサにより構成されてもよい。 The optical sensor 22 comprises, for example, optical sensors 22a, 22b, 22c, each highly sensitive to different wavelengths. The optical sensors 22a, 22b, and 22c detect visible light, reflected light, and thermal radiation condensed by the condensing lenses 19-21, respectively, and generate electrical signals corresponding to the intensity of the detected light. Note that the optical sensor 22 may be composed of one optical sensor capable of detecting the intensity for each wavelength.
　光センサ２２により生成された電気信号は、伝送ケーブル２３を介してコントローラ２４に伝送される。コントローラ２４は、ハードウェアコントローラであり、分光装置４０全体の動作を統括制御する。コントローラ２４は、ＣＰＵ及び通信回路等を含み、光センサ２２から受けとった電気信号を、判定装置５０に送信する。コントローラ２４は、例えばＡ／Ｄ変換器を備えて、アナログの電気信号をデジタル信号（単に「信号」ともいう）に変換する。なお、デジタル信号に変換する際のサンプリング周期は、加工状態の判定において、加工プロセスの特徴及び物理量の局所的な値の傾向を捉えるために十分なサンプル数を確保する観点から、例えばレーザ光６の出力制御を行う時間の１００分の１以下が好ましい。 The electrical signal generated by the optical sensor 22 is transmitted to the controller 24 via the transmission cable 23. The controller 24 is a hardware controller and controls the overall operation of the spectroscopic device 40 . The controller 24 includes a CPU, a communication circuit, etc., and transmits an electrical signal received from the optical sensor 22 to the determination device 50 . The controller 24 has an A/D converter, for example, and converts analog electrical signals into digital signals (also simply referred to as “signals”). The sampling period for conversion into a digital signal is, for example, a laser beam 6 from the viewpoint of securing a sufficient number of samples to capture the characteristics of the machining process and the tendency of local values of physical quantities in determining the machining state. is preferably 1/100 or less of the time for performing the output control.
　１－４．判定装置の構成
　図４は、本実施形態の判定装置５０の構成を例示するブロック図である。判定装置５０は、例えばコンピュータのような情報処理装置で構成される。判定装置５０は、演算の処理を行うＣＰＵ５１と、他の機器と通信を行うための通信回路５２と、データ及びコンピュータプログラムを記憶する記憶装置５３とを備える。 1-4. Configuration of Determination Device FIG. 4 is a block diagram illustrating the configuration of the determination device 50 of the present embodiment. The determination device 50 is configured by an information processing device such as a computer, for example. The determination device 50 includes a CPU 51 that performs arithmetic processing, a communication circuit 52 that communicates with other devices, and a storage device 53 that stores data and computer programs.
　ＣＰＵ５１は、本実施形態における判定装置の演算回路の一例である。ＣＰＵ５１は、記憶装置５３に格納された制御プログラム５６の実行により、判定モデル５７の訓練及び実行を含む所定の機能を実現する。判定装置５０は、ＣＰＵ５１が制御プログラム５６を実行することで、本実施形態における判定装置としての機能を実現する。なお、本実施形態でＣＰＵ５１として構成される演算回路は、ＭＰＵまたはＧＰＵ等の種々のプロセッサで実現されてもよく、１つまたは複数のプロセッサで構成されてもよい。 The CPU 51 is an example of an arithmetic circuit of the determination device in this embodiment. The CPU 51 implements a predetermined function including training and execution of the judgment model 57 by executing the control program 56 stored in the storage device 53 . The CPU 51 executes the control program 56 so that the determination device 50 realizes the function of the determination device in the present embodiment. Note that the arithmetic circuit configured as the CPU 51 in this embodiment may be realized by various processors such as an MPU or GPU, or may be configured by one or a plurality of processors.
　通信回路５２は、例えばＩＥＥＥ８０２．１１、４Ｇ、または５Ｇ等の規格に準拠して通信を行う通信回路である。通信回路５２は、例えばイーサネット（登録商標）等の規格に従って有線通信を行ってもよい。通信回路５２は、インターネット等の通信ネットワークに接続可能である。また、判定装置５０は、通信回路５２を介して他の機器と直接通信を行ってもよく、アクセスポイント経由で通信を行ってもよい。なお、通信回路５２は、通信ネットワークを介さずに他の機器と通信可能に構成されてもよい。例えば、通信回路５２は、ＵＳＢ（登録商標）端子及びＨＤＭＩ（登録商標）端子等の接続端子を含んでもよい。 The communication circuit 52 is a communication circuit that performs communication in compliance with standards such as IEEE802.11, 4G, or 5G. The communication circuit 52 may perform wired communication according to a standard such as Ethernet (registered trademark). The communication circuit 52 can be connected to a communication network such as the Internet. Further, the determination device 50 may directly communicate with another device via the communication circuit 52, or may communicate via an access point. Note that the communication circuit 52 may be configured to be able to communicate with other devices without going through a communication network. For example, the communication circuit 52 may include connection terminals such as a USB (registered trademark) terminal and an HDMI (registered trademark) terminal.
　記憶装置５３は、判定システム１００の機能を実現するために必要なコンピュータプログラム及びデータを記憶する記憶媒体であり、ＣＰＵ５１で実行される制御プログラム５６、及び各種のデータを格納している。記憶装置５３は、判定モデル５７の構築後は判定モデル５７を格納する。判定モデル５７は、溶融形状異常が発生している状況下での信号から算出された特徴量と、溶融形状異常が発生したときの加工状態とを含む訓練データに基づいて構築される。判定モデル５７の詳細は後述する。 The storage device 53 is a storage medium for storing computer programs and data necessary for realizing the functions of the determination system 100, and stores a control program 56 executed by the CPU 51 and various data. The storage device 53 stores the judgment model 57 after the judgment model 57 is constructed. The judgment model 57 is constructed based on training data including the feature amount calculated from the signal under the condition where the melting shape anomaly occurs and the processing state when the melting shape anomaly occurs. The details of the judgment model 57 will be described later.
　記憶装置５３は、例えばハードディスクドライブ（ＨＤＤ）のような磁気記憶装置、光ディスクドライブのような光学的記憶装置またはＳＳＤのような半導体記憶装置で構成される。記憶装置５３は、例えばＤＲＡＭまたはＳＲＡＭ等のＲＡＭにより構成される一時的な記憶素子を備えてもよく、ＣＰＵ５１の内部メモリとして機能してもよい。 The storage device 53 is composed of, for example, a magnetic storage device such as a hard disk drive (HDD), an optical storage device such as an optical disk drive, or a semiconductor storage device such as an SSD. The storage device 53 may include a temporary storage element configured by RAM such as DRAM or SRAM, and may function as an internal memory of the CPU 51 .
　２．動作
　以上のように構成される判定システム１００において、例えば図１に示すように、分光装置４０は、光センサ２２により、レーザ光６の照射により溶融部２７において発生する熱放射、可視光及び反射光を検出する。分光装置４０は、検出した熱放射、可視光及び反射光の強度に応じた信号を判定装置５０に送信する。本システム１００における判定装置５０の動作を、以下に説明する。 2. Operation In the determination system 100 configured as described above, for example, as shown in FIG. Detect light. The spectroscopic device 40 transmits to the determination device 50 a signal corresponding to the intensity of the detected thermal radiation, visible light and reflected light. The operation of the determination device 50 in this system 100 will be described below.
　２－１．判定処理
　以下では、判定装置５０において、溶融形状異常の位置、数及びサイズを判定する判定処理について、図５～図８を用いて説明する。 2-1. Judgment Processing The judgment processing for judging the position, number, and size of the melt shape abnormality in the judgment device 50 will be described below with reference to FIGS. 5 to 8. FIG.
　図５は、本実施形態の判定装置５０における判定処理を例示するフローチャートである。本フローチャートに示す各処理は、例えば判定装置５０のＣＰＵ５１により実行される。本フローチャートは、例えば、通信回路５２を介して接続された入力装置から、判定システム１００のユーザ等により判定処理を開始するための所定の操作が入力されることで開始される。 FIG. 5 is a flowchart illustrating determination processing in the determination device 50 of this embodiment. Each process shown in this flowchart is executed by the CPU 51 of the determination device 50, for example. This flowchart is started, for example, when the user of the determination system 100 or the like inputs a predetermined operation for starting determination processing from an input device connected via the communication circuit 52 .
　まず、ＣＰＵ５１は、通信回路５２により、分光装置４０の光センサ２２で検知された熱放射、可視光及び反射光に対応する信号を取得する（Ｓ１）。 First, the CPU 51 acquires signals corresponding to thermal radiation, visible light, and reflected light detected by the optical sensor 22 of the spectroscopic device 40 through the communication circuit 52 (S1).
　図６は、判定装置５０において取得される信号を説明するための図である。図６の（Ａ）は、加工時に溶融形状異常が発生した場合の熱放射、可視光及び反射光の何れかに対応する信号の信号波形を例示する。図６の（Ｂ）は、溶融形状異常が発生しない場合での熱放射、可視光及び反射光の何れかの信号波形を例示する。図６の（Ｃ）は、被加工物７０に照射されたレーザ光６の出力を示す。図６の（Ａ）、（Ｂ）の信号は、図６の（Ｃ）のレーザ出力により発生した熱放射、可視光及び反射光の何れかに対応する。 FIG. 6 is a diagram for explaining signals acquired by the determination device 50. FIG. (A) of FIG. 6 illustrates signal waveforms of signals corresponding to any one of thermal radiation, visible light, and reflected light when a melting shape abnormality occurs during processing. (B) of FIG. 6 illustrates signal waveforms of any one of thermal radiation, visible light, and reflected light when no melt shape abnormality occurs. (C) of FIG. 6 shows the output of the laser beam 6 with which the workpiece 70 is irradiated. The signals of FIGS. 6A and 6B correspond to either thermal radiation, visible light, or reflected light generated by the laser output of FIG. 6C.
　図６の（Ａ）～（Ｃ）において、横軸は時間を示し、縦軸は信号強度（図６の（Ａ）、（Ｂ））またはレーザ出力（図６の（Ｃ））を示す。また、時間Ｔ１はレーザ光６の１パルスに相当する時間区間を示し、時間Ｔ２はレーザ出力の立ち上がりと立下りを除くピーク出力の時間区間を示す。ここで、本実施形態のレーザ加工装置３０では、時間Ｔ１において、被加工物７０ごとの溶接が行われる。ステップＳ１においてＣＰＵ５１は、被加工物７０ごとの溶接時間に対応した時間Ｔ１における熱放射、可視光及び反射光の変化を示す信号を取得する。 In (A) to (C) of FIG. 6, the horizontal axis indicates time, and the vertical axis indicates signal intensity ((A) and (B) in FIG. 6) or laser output ((C) in FIG. 6). Also, time T1 indicates a time interval corresponding to one pulse of the laser light 6, and time T2 indicates a time interval of peak output excluding rise and fall of the laser output. Here, in the laser processing apparatus 30 of the present embodiment, welding for each workpiece 70 is performed at time T1. In step S1, the CPU 51 acquires signals indicating changes in heat radiation, visible light, and reflected light at time T1 corresponding to the welding time for each workpiece 70. FIG.
　図６の（Ａ）に示すように、溶融形状異常が発生すると、図６の（Ｂ）の正常時と比較して、信号強度が一時的に増加するピークを生じた波形の信号が取得される。溶融形状異常の発生時における信号のピークは、例えば当該異常を引き起こす異物８０による発光に起因する。なお、溶融形状異常の発生時、異物８０により発光が瞬間的に減衰することで、一時的に減衰ピークが生じる場合もある。この場合、信号強度は一時的に減少するピークを生じた波形の信号が取得される。このような場合においても、後述する図５のフローチャートに示すフローについて、局所的な最小値を抽出し、区間Ｔｐの信号強度に平均値Ｓａを減じた値において積分値を算出すれば良い。以下のフローにおいては、一例として信号強度が一時的に増加するピークを生じた場合の波形の信号について、フローの説明を行う。 As shown in (A) of FIG. 6, when a melt shape abnormality occurs, a waveform signal having a peak in which the signal intensity temporarily increases compared to the normal state shown in (B) of FIG. 6 is obtained. be. A signal peak at the time of occurrence of a melting shape anomaly is caused by, for example, light emission by the foreign matter 80 that causes the anomaly. It should be noted that when the melt shape abnormality occurs, the light emission is momentarily attenuated by the foreign matter 80, and an attenuation peak may occur temporarily. In this case, a signal having a waveform with a temporarily decreasing peak is obtained. Even in such a case, the integrated value can be calculated by extracting the local minimum value and subtracting the average value Sa from the signal intensity in the section Tp, in the flow shown in the flowchart of FIG. 5, which will be described later. In the following flow, as an example, the flow will be described for a signal having a waveform when a peak in which the signal intensity increases temporarily occurs.
　図５のフローチャートにおいて、次に、ＣＰＵ５１は、取得した信号から、判定モデル５７に入力する特徴量を算出する（Ｓ２）。本実施形態では、ＣＰＵ５１は、特徴量として、正規化といった前処理を適用した信号強度に加えて、ピークにおける信号強度に基づく強度値（以降、「ピーク強度値」という）を算出する。 In the flowchart of FIG. 5, the CPU 51 next calculates the feature amount to be input to the determination model 57 from the acquired signal (S2). In this embodiment, the CPU 51 calculates an intensity value based on the signal intensity at the peak (hereinafter referred to as "peak intensity value") in addition to the signal intensity to which preprocessing such as normalization is applied, as the feature quantity.
　図７は、判定装置５０において特徴量を算出する処理（Ｓ２）を説明するための図である。図７の（Ａ）は、図６の（Ａ）と同様に、溶融形状異常が発生した場合における熱放射、可視光または反射光に対応する信号の信号強度の時間変化を示す。図７を用いて、図５のステップＳ２においてピーク強度値の特徴量を算出する処理について説明する。 FIG. 7 is a diagram for explaining the processing (S2) for calculating the feature amount in the determination device 50. FIG. FIG. 7(A), like FIG. 6(A), shows changes over time in the signal intensity of the signal corresponding to thermal radiation, visible light, or reflected light when a melt shape abnormality occurs. Processing for calculating the feature amount of the peak intensity value in step S2 of FIG. 5 will be described with reference to FIG.
　ＣＰＵ５１は、まず、取得した信号のピークを検出する処理を行う。ＣＰＵ５１は、例えばサンプリング周期ごとの信号強度の値を比較する演算を行って、時間的に隣接する前後の点よりも値が大きい点を局所的な最大値として抽出する。この際、局所的な最大値として抽出される値を所定の信号強度以上に制限する観点から、閾値が設定されてもよい。ＣＰＵ５１は、例えば、局所的な最大値と同様に信号強度の局所的な最小値を抽出して、局所的な最大値と隣接する２点に挟まれた区間Ｔｐにおける信号波形の領域として、ピークを検出する。区間Ｔｐは、ピークの発生時間に対応する。図７の（Ｂ）は、図７の（Ａ）の信号において区間Ｔｐのピークを検出した例を示す。 The CPU 51 first performs processing to detect the peak of the acquired signal. The CPU 51, for example, performs an operation to compare the signal strength values for each sampling period, and extracts a point having a larger value than the temporally adjacent points before and after as a local maximum value. At this time, a threshold value may be set from the viewpoint of limiting the value extracted as the local maximum value to a predetermined signal strength or more. The CPU 51, for example, extracts the local minimum value of the signal intensity in the same manner as the local maximum value, and extracts the peak to detect Interval Tp corresponds to the peak occurrence time. (B) of FIG. 7 shows an example in which the peak of section Tp is detected in the signal of (A) of FIG.
　ピークの検出後、ＣＰＵ５１は、ピークを除く信号強度の平均値Ｓａを算出する。平均値Ｓａは、例えば、レーザ光６の１パルスのうちピーク出力の時間Ｔ２から、区間Ｔｐを除いた時間（Ｔ２－Ｔｐ）における信号強度の平均値として算出される。図７の（Ｃ）は、図７の（Ｂ）の例において平均値Ｓａを算出した例を示す。 After detecting the peak, the CPU 51 calculates the average value Sa of the signal intensity excluding the peak. The average value Sa is calculated, for example, as an average value of signal intensities at a time (T2−Tp) excluding the section Tp from the time T2 of the peak output in one pulse of the laser beam 6 . (C) of FIG. 7 shows an example of calculating the average value Sa in the example of (B) of FIG.
　続いて、ＣＰＵ５１は、ピーク強度値として、区間Ｔｐの信号強度から、ピークを除く信号強度の平均値Ｓａを減じた値において、ピークの発生時間に対応する区間Ｔｐについて算出した積分値を算出する。図７の（Ｄ）は、図７の（Ｃ）の例において積分値を算出する例を示す。当該積分値は、図７の（Ｄ）に示す領域Ｒｐの面積に対応する。 Subsequently, the CPU 51 calculates, as a peak intensity value, the integrated value calculated for the section Tp corresponding to the peak occurrence time, with the value obtained by subtracting the average value Sa of the signal strength excluding the peak from the signal strength of the section Tp. . (D) of FIG. 7 shows an example of calculating the integral value in the example of (C) of FIG. 7 . The integrated value corresponds to the area of the region Rp shown in (D) of FIG.
　以上のような特徴量の算出後（Ｓ２）、ＣＰＵ５１は、特徴量を判定モデル５７に入力して、溶融形状異常の位置、数及びサイズを判定する判定モデルの処理（Ｓ３）を行う。信号強度の特徴量は、例えばＡ／Ｄ変換におけるサンプリング周期ごとの信号波形の振幅として、判定モデル５７に入力される。 After calculating the feature amount as described above (S2), the CPU 51 inputs the feature amount to the determination model 57 and performs determination model processing (S3) for determining the position, number, and size of the molten shape abnormality. The feature quantity of the signal intensity is input to the determination model 57 as, for example, the amplitude of the signal waveform for each sampling period in A/D conversion.
　図８は、判定モデルの処理（Ｓ３）を説明するための図である。図８の（Ａ）は、図６の（Ａ）と同様に溶融形状異常が発生したときの信号波形を示す。図８の（Ｂ）は、図８の（Ａ）の信号が生成された際の加工後における被加工物７０のレーザ加工装置３０側の部材７０ａの外観を模式的に示す。図８の（Ｂ）では、溶融長Ｗｘと溶融幅Ｗｙを有する溶接領域２７０において、溶融形状異常の例として穴８５が発生している。 FIG. 8 is a diagram for explaining the judgment model processing (S3). FIG. 8(A) shows a signal waveform when a melting shape abnormality occurs as in FIG. 6(A). (B) of FIG. 8 schematically shows the appearance of a member 70a of the workpiece 70 on the side of the laser processing apparatus 30 after processing when the signal of (A) of FIG. 8 is generated. In (B) of FIG. 8, a hole 85 is generated as an example of a melt shape abnormality in a weld region 270 having a melt length Wx and a melt width Wy.
　本実施形態のレーザ加工装置３０は、１パルスに相当する時間Ｔ１において、被加工物７０ごとに溶融長Ｗｘにわたる溶接を行う。図８の（Ａ）の例では、レーザ加工装置３０が図８の（Ｂ）におけるｘ軸の正方向に加工を進めたときに穴８５が発生したことに対応して、区間Ｔｐのピークが生じ、ステップＳ２において検出されている。 The laser processing apparatus 30 of this embodiment performs welding over the fusion length Wx for each workpiece 70 in the time T1 corresponding to one pulse. In the example of (A) of FIG. 8, the peak of the section Tp corresponds to the occurrence of the hole 85 when the laser processing apparatus 30 advances the processing in the positive direction of the x-axis in (B) of FIG. arises and is detected in step S2.
　図８の例では、判定モデルの処理（Ｓ３）において、ＣＰＵ５１は、図８の（Ａ）の信号から算出した信号強度及びピーク強度値の特徴量を判定モデル５７に入力して、図８の（Ｂ）の穴８５の位置、数、及びサイズを判定する。位置は、例えば部材７０ａ上の溶接開始点を原点とする直交座標系において、穴８５の重心の座標として判定される。サイズは、例えば穴８５の面積として判定される。数は、図８の（Ｂ）では穴８５の他に溶融形状異常がないことから「１」と判定される。 In the example of FIG. 8, in the judgment model processing (S3), the CPU 51 inputs the feature amounts of the signal intensity and the peak intensity value calculated from the signal of FIG. Determine location, number and size of holes 85 in (B). The position is determined, for example, as the coordinates of the center of gravity of the hole 85 in an orthogonal coordinate system whose origin is the welding start point on the member 70a. The size is determined as the area of the hole 85, for example. The number is determined to be "1" in FIG.
　図５に戻り、ＣＰＵ５１は、穴８５といった溶融形状異常の位置、数及びサイズの判定結果を、通信回路５２により出力する（Ｓ４）。判定結果は、例えば外部の情報処理装置または表示機器等により受信されて、表示され得る。また、判定装置５０がＣＰＵ５１と通信可能な表示装置（例えばディスプレイ）を備え、表示装置に判定結果を表示させてもよい。 Returning to FIG. 5, the CPU 51 outputs the determination result of the position, number and size of the abnormal shape of the melt such as the hole 85 through the communication circuit 52 (S4). The determination result can be received and displayed by, for example, an external information processing device or display device. Further, the determination device 50 may be provided with a display device (for example, a display) that can communicate with the CPU 51, and the determination result may be displayed on the display device.
　その後、ＣＰＵ５１は、図５のフローチャートを終了する。図５のフローチャートは、例えば、被加工物７０ごとの溶接加工を行う度に繰り返し実行される。 After that, the CPU 51 ends the flowchart of FIG. The flowchart of FIG. 5 is repeatedly executed, for example, every time welding is performed for each workpiece 70 .
　以上の判定処理によると、本実施形態の判定装置５０は、分光装置４０の光センサ２２により生成された信号を取得して（Ｓ１）、信号から特徴量を算出し（Ｓ２）、その特徴量に基づいて判定モデル５７により溶融形状異常の位置、数及びサイズを判定する（Ｓ３）。これにより、判定装置５０は、重ね合わせ溶接のためのレーザ加工において溶融形状異常に関する加工状態を詳細に判定することができる。 According to the determination process described above, the determination device 50 of the present embodiment acquires the signal generated by the optical sensor 22 of the spectroscopic device 40 (S1), calculates the feature amount from the signal (S2), and calculates the feature amount (S3). Thereby, the determination device 50 can determine in detail the processing state related to the melt shape abnormality in laser processing for lap welding.
　なお、図５のステップＳ２において、特徴量は熱放射、可視光及び反射光の全てについて算出されてもよく、熱放射、可視光及び反射光のいずれか１つについてのみ算出されてもよい。また、判定モデルの処理（Ｓ３）において、判定モデル５７は、例えば溶融形状異常の位置及び数のみを判定してもよい。 Note that in step S2 of FIG. 5, the feature amount may be calculated for all of thermal radiation, visible light, and reflected light, or may be calculated for any one of thermal radiation, visible light, and reflected light. In addition, in the judgment model processing (S3), the judgment model 57 may judge only the position and number of melt shape abnormalities, for example.
　また、ステップＳ２において、上述した減衰ピークについても検出して信号強度の積分値を算出してもよい。この場合、減衰ピークについての値は負となる一方、図７の例で説明した増加ピークについて算出するピーク強度値は正となる。このようにすれば、信号強度の減衰によるピークと増加によるピークとを区別して、異物８０による発光の変化を特徴量に反映させることができる。なお、減衰ピークを検出する場合であっても、ピークについての信号強度の積分値は、これに限らず、例えばピークの存在と大きさのみに着目して、その絶対値が特徴量に用いられてもよい。 Also, in step S2, the above-described attenuation peak may also be detected to calculate the integrated value of the signal intensity. In this case, the value for the attenuation peak will be negative, while the peak intensity value calculated for the increase peak described in the example of FIG. 7 will be positive. In this way, it is possible to distinguish between peaks due to attenuation and peaks due to increase in signal intensity, and to reflect changes in light emission due to the foreign matter 80 in the feature amount. Even in the case of detecting an attenuation peak, the integrated value of the signal intensity for the peak is not limited to this, and for example, focusing only on the presence and size of the peak, the absolute value is used as the feature amount. may
　２－２．訓練処理
　以下、判定モデル５７を構築するための訓練処理について、図９及び図１０を用いて説明する。 2-2. Training Processing The training processing for constructing the judgment model 57 will be described below with reference to FIGS. 9 and 10. FIG.
　図９は、判定モデル５７の訓練処理を例示するフローチャートである。本フローチャートの各処理は、例えば判定装置５０のＣＰＵ５１によって実行される。 FIG. 9 is a flowchart illustrating training processing of the judgment model 57. FIG. Each process of this flowchart is executed by the CPU 51 of the determination device 50, for example.
　まず、ＣＰＵ５１は、例えば記憶装置５３に予め格納された訓練データを取得する（Ｓ１１）。 First, the CPU 51 acquires training data stored in advance, for example, in the storage device 53 (S11).
　訓練データは、熱放射、可視光及び反射光の信号強度及びピーク強度値といった特徴量と、加工状態として溶融形状異常の位置、数及びサイズとを対応付けたデータである。訓練データは、加工状態が変化する複数の条件下で、レーザ加工を行って検出された熱放射、可視光及び反射光に基づく信号から算出された特徴量と、加工後に溶接領域２７０の外観測定により判定された加工状態とを関連付けて記録することで構築される。外観測定は、例えば光学顕微鏡による溶接領域２７０の観察、または溶接領域２７０を撮影した画像における測定により実施され得るが、特にこれに限らない。 The training data is data that associates the feature values such as the signal intensity and peak intensity value of thermal radiation, visible light, and reflected light with the position, number, and size of molten shape anomalies as processing conditions. The training data includes feature values calculated from signals based on thermal radiation, visible light, and reflected light detected by laser processing under a plurality of conditions in which the processing state changes, and the appearance measurement of the welded region 270 after processing. It is constructed by recording in association with the machining state determined by. Appearance measurement can be performed, for example, by observing the welded region 270 with an optical microscope or by measuring an image of the welded region 270, but is not limited to this.
　図１０は、溶融形状異常の発生時において生成される信号を説明するための図である。訓練データの構築において、図１０に例示するような種々の波形パターンを有する信号に基づく特徴量と、対応する加工状態とが収集される。 FIG. 10 is a diagram for explaining signals generated when a melt shape abnormality occurs. In constructing the training data, features based on signals having various waveform patterns as illustrated in FIG. 10 and corresponding machining states are collected.
　図１０の（Ａ）では、それぞれ熱放射、可視光及び反射光の強度に応じて生成される信号Ｌｔ、Ｌｖ及びＬｒの全てにおいて、１つの溶融形状異常に対応するピークが検出される。図１０の（Ｂ）では、熱放射及び可視光の２つの信号Ｌｔ、Ｌｖにおいて、１つの溶融形状異常のピークが検出される。図１０の（Ｃ）では、反射光の信号Ｌｒのみにおいて、１つの溶融形状異常のピークが検出される。図１０の（Ｄ）では、熱放射、可視光及び反射光の信号Ｌｔ、Ｌｖ、Ｌｒのそれぞれにおいて、２つの溶融形状異常に対応する２つのピークが検出される。図１０の（Ａ）、（Ｄ）に示すように、反射光の信号Ｌｒでは、熱放射及び可視光の信号Ｌｔ、Ｌｖと比較して早い時間においてピークが発生する傾向がある。 In (A) of FIG. 10, a peak corresponding to one melt shape anomaly is detected in all of the signals Lt, Lv, and Lr generated according to the intensity of thermal radiation, visible light, and reflected light, respectively. In (B) of FIG. 10, one melting shape anomaly peak is detected in the two signals Lt and Lv of thermal radiation and visible light. In (C) of FIG. 10, one melting shape abnormality peak is detected only in the reflected light signal Lr. In (D) of FIG. 10, two peaks corresponding to two melting shape anomalies are detected in each of the thermal radiation, visible light, and reflected light signals Lt, Lv, and Lr. As shown in FIGS. 10A and 10D, the reflected light signal Lr tends to peak at earlier times than the thermal radiation and visible light signals Lt and Lv.
　このような多様なピークの検出パターンを伴う信号に基づく特徴量と対応する加工状態とを訓練データに含めることで、後述の処理により、ピークが検出される光、時間及び数等の条件が変化しても加工状態を詳細に判定可能な判定モデル５７を生成し得る。また、本実施形態では、熱放射、可視光及び反射光の３つに基づく特徴量を用いることで、熱放射、可視光及び反射光の１つまたは２つの信号においてのみピークが検出される場合であっても溶融形状異常が発生する傾向を判定モデル５７に反映し得る。訓練データには、例えば実際の加工時に想定されるピーク数として２つ以下のピークを含むデータが用いられるが、特にこれに限らず、３つ以上のピークを含むデータが用いられてもよい。また、１つのピークとみなす時間の区間が予め設定されてもよい。 By including feature amounts based on signals with such various peak detection patterns and corresponding processing states in the training data, the conditions such as light, time, and number of peaks detected by the processing described later can be changed. However, it is possible to generate a determination model 57 that can determine the machining state in detail. In addition, in this embodiment, by using feature amounts based on three of thermal radiation, visible light, and reflected light, peaks are detected only in one or two signals of thermal radiation, visible light, and reflected light. However, the judgment model 57 can reflect the tendency of the melt shape abnormality to occur. For training data, for example, data containing two or less peaks is used as the number of peaks assumed during actual processing, but data containing three or more peaks may also be used. Also, a time interval regarded as one peak may be set in advance.
　ＣＰＵ５１は、訓練データを取得すると（Ｓ１）、訓練データを用いて機械学習を行い、判定モデル５７を生成する（Ｓ２）。判定モデル５７は、例えば、ランダムフォレストまたはニューラルネットワーク等に基づく回帰モデルとして生成される。 When the CPU 51 acquires the training data (S1), it performs machine learning using the training data to generate the judgment model 57 (S2). The judgment model 57 is generated as a regression model based on, for example, random forest or neural network.
　以上の訓練処理によると、レーザ加工において検出された熱放射、可視光及び反射光に対応する信号に基づく特徴量から、溶融形状異常の位置、数及びサイズを判定する学習済みモデルとして、判定モデル５７を生成することができる。 According to the above training process, from the feature values based on the signals corresponding to thermal radiation, visible light, and reflected light detected in laser processing, the position, number, and size of the abnormal shape of the melt can be determined as a learned model. 57 can be generated.
　なお、判定モデル５７の訓練処理は、判定装置５０とは別の情報処理装置において実行されてもよい。判定装置５０は、例えば通信ネットワークを介して、通信回路５２により構築済みの判定モデルを取得してもよい。 Note that the training process for the determination model 57 may be executed in an information processing device different from the determination device 50 . The determination device 50 may acquire the built determination model by the communication circuit 52, for example, via a communication network.
　また、判定モデル５７の訓練データには、溶融形状異常が生じていない場合の特徴量と溶融形状異常が生じていない場合の加工状態が含まれていてもよい。溶融形状異常が生じていない場合の特徴量は、例えばピーク強度値「０」であってもよい。溶融形状異常が生じていない場合の加工状態は、例えば溶融形状異常の位置「０」、数「０」及びサイズ「０」であってもよい。 In addition, the training data for the determination model 57 may include the feature amount when no melting shape anomaly has occurred and the processing state when no melting shape anomaly has occurred. For example, the feature value when no melting shape abnormality has occurred may be a peak intensity value of “0”. A processing state in which no melt shape anomaly has occurred may be, for example, a position of '0', a number of melt shape anomalies of '0', and a size of '0'.
　３．効果等
　以上のように、本実施形態において、判定処理（Ｓ１～Ｓ４）は、重ね合わせ溶接のためのレーザ加工における加工状態の判定方法を提供する。本方法は、光センサ２２を用いて、レーザ光６が被加工物７０に照射されることで被加工物７０の表面に形成される溶融部２７（溶接部の一例）において発生する熱放射（熱放射光）、可視光及び反射光のうち、少なくとも１つを検出する工程と、被加工物７０ごとの溶接時間に対応した時間Ｔ１（時間区間）における熱放射、可視光及び反射光の変化を示す信号を光センサ２２から取得する工程（Ｓ１）と、加工状態を判定する判定モデル５７に信号に基づく信号の信号強度を含む特徴量を入力して、被加工物７０の重ね合わせ面に異物８０が存在する場合に生じる溶融形状異常の、溶融長Ｗｘと溶融幅Ｗｙを有する溶接領域２７０における溶融形状異常の位置及び数を、加工状態として、判定する工程（Ｓ２、Ｓ３）と、判定した溶融形状異常の位置及び数を判定結果として出力する工程（Ｓ４）とを含む。判定モデル５７は、溶融形状異常が発生している状況下で算出された特徴量と溶融形状異常が発生している状況下での加工状態とを含む訓練データに基づいて構築される。 3. Effects, Etc. As described above, in the present embodiment, the determination processing (S1 to S4) provides a method for determining the processing state in laser processing for lap welding. This method uses the optical sensor 22 to detect heat radiation ( A step of detecting at least one of thermal radiation light), visible light and reflected light, and changes in the thermal radiation, visible light and reflected light at time T1 (time interval) corresponding to the welding time for each workpiece 70 A step (S1) of acquiring a signal indicating from the optical sensor 22, and inputting a feature amount including the signal intensity of the signal based on the signal to the determination model 57 for determining the machining state, Steps (S2, S3) for determining, as a processing state, the position and number of the abnormal molten shape in the welding region 270 having the molten length Wx and the molten width Wy of the abnormal molten shape that occurs when the foreign matter 80 is present; and a step (S4) of outputting the positions and number of the melt shape abnormalities detected as a determination result. The determination model 57 is constructed based on training data including feature values calculated under conditions in which abnormalities in the molten shape occur and processing states in conditions in which the abnormalities in the molten shape occur.
　以上の方法によると、レーザ光６の照射により発生して検知された熱放射、可視光及び反射光のうち１つ以上に基づく信号を取得して（Ｓ１）、信号強度を含む特徴量を算出し、加工状態として溶融形状異常の位置及び数を判定する（Ｓ２、Ｓ３）。これにより、重ね合わせ溶接のためのレーザ加工において検出された熱放射、可視光及び反射光のうち少なくとも１つの信号強度に基づいて、溶融形状異常に関する加工状態を詳細に判定することができる。 According to the above method, a signal based on one or more of thermal radiation, visible light, and reflected light generated and detected by the irradiation of the laser beam 6 is acquired (S1), and the feature amount including the signal intensity is calculated. Then, the position and number of melt shape abnormalities are determined as the processing state (S2, S3). Accordingly, it is possible to determine in detail the processing state related to the melt shape abnormality based on the signal intensity of at least one of thermal radiation, visible light, and reflected light detected in laser processing for lap welding.
　本実施形態において、判定の工程（Ｓ２、Ｓ３）は、信号のピークを検出し、加工状態としてさらに、溶融形状異常のサイズを判定することを含む。出力の工程（Ｓ４）は、判定結果としてさらに、判定した溶融形状異常のサイズを出力することを含む。特徴量は、ピークにおける信号の信号強度に基づく強度値の一例であるピーク強度値を含む。これにより、ピーク強度値に基づいて、溶融形状異常のサイズを含め加工状態をより詳細に判定することができる。 In this embodiment, the determination steps (S2, S3) include detecting the peak of the signal and determining the size of the melt shape abnormality as the processing state. The step of outputting (S4) further includes outputting the determined size of the melt shape abnormality as a determination result. The feature quantity includes a peak intensity value, which is an example of an intensity value based on the signal intensity of the signal at the peak. As a result, the processing state including the size of the melt shape abnormality can be determined in more detail based on the peak intensity value.
　本実施形態において、強度値は、ピークの信号強度からピークを除く信号の信号強度の平均値Ｓａを減じた値が、区間Ｔｐ（ピークの発生時間）について積分されることにより得られた積分値である（図７参照）。これにより、異物８０による溶融形状異常の発生に伴う発光の強度を特徴量に反映して、溶融形状異常のサイズ等の加工状態を詳細に判定しやすくすることができる。 In the present embodiment, the intensity value is an integrated value obtained by subtracting the average value Sa of the signal intensity of the signal excluding the peak from the signal intensity of the peak, and integrating it over the interval Tp (peak occurrence time). (see FIG. 7). As a result, the intensity of the light emitted by the foreign matter 80 caused by the occurrence of the abnormal molten shape can be reflected in the feature amount, making it easier to determine the processing state such as the size of the abnormal molten shape in detail.
　本実施形態において、判定モデル５７は、加工状態が変化する複数の条件における各条件のもとで、レーザ加工を行って検出された熱放射、可視光及び反射光のうち少なくとも１つに基づく信号から算出された特徴量と、溶接領域２７０の外観測定により判定された加工状態と、を関連付けた訓練データを用いた機械学習により生成される学習済みモデルを含む。これにより、熱放射、可視光及び反射光の少なくとも１つに基づく特徴量から、加工状態を判定する判定モデル５７が得られる。 In this embodiment, the determination model 57 is a signal based on at least one of thermal radiation, visible light, and reflected light detected by performing laser processing under each of a plurality of conditions in which the processing state changes. and the machined state determined by the appearance measurement of the welding region 270 are associated with each other. As a result, a determination model 57 for determining the machining state is obtained from feature amounts based on at least one of thermal radiation, visible light, and reflected light.
　本実施形態の判定システム１００において、判定装置５０は、重ね合わせ溶接のためのレーザ加工における加工状態の判定装置の一例である。判定装置５０は、演算回路の一例としてＣＰＵ５１と、通信回路５２とを備える。通信回路５２は、レーザ光６が被加工物７０に照射されることで被加工物７０の表面に形成される溶融部２７（溶接部の一例）において発生する熱放射（熱放射光）、可視光及び反射光のうち、少なくとも１つを光センサ２２により検出して生成された信号を受け付ける。信号は、被加工物７０ごとの溶接時間に対応した時間区間の一例として時間Ｔ１における熱放射、可視光及び反射光の少なくとも１つの変化を示す信号である。ＣＰＵ５１は、通信回路５２により、信号を取得し（Ｓ１）、加工状態を判定する判定モデル５７に信号に基づく信号の信号強度を含む特徴量を入力して、被加工物７０の重ね合わせ面に異物８０が存在する場合に生じる溶融形状異常の、溶融長Ｗｘと溶融幅Ｗｙを有する溶接領域２７０における位置及び数を、加工状態として、判定し（Ｓ２、Ｓ３）、判定した溶融形状異常の位置及び数を判定結果として、通信回路５２により出力する（Ｓ４）。判定モデル５７は、溶融形状異常が発生している状況下で算出された特徴量と溶融形状異常が発生している状況下での加工状態とを含む訓練データに基づいて構築される。 In the determination system 100 of the present embodiment, the determination device 50 is an example of a processing state determination device in laser processing for lap welding. The determination device 50 includes a CPU 51 as an example of an arithmetic circuit and a communication circuit 52 . The communication circuit 52 transmits thermal radiation (thermal radiation light) generated in a melted portion 27 (an example of a welded portion) formed on the surface of the workpiece 70 by irradiating the workpiece 70 with the laser beam 6. A signal generated by detecting at least one of light and reflected light by the optical sensor 22 is received. The signal is a signal that indicates changes in at least one of thermal radiation, visible light, and reflected light at time T1 as an example of a time interval corresponding to welding time for each workpiece 70 . The CPU 51 acquires the signal through the communication circuit 52 (S1), inputs the feature amount including the signal strength of the signal based on the signal to the judgment model 57 for judging the machining state, and makes the overlapped surface of the workpiece 70. The position and number of the melt shape anomalies in the welding region 270 having the melt length Wx and the melt width Wy, which occur when the foreign matter 80 is present, are determined as the processing state (S2, S3), and the determined melt shape anomalies are determined. and the number as a determination result are output by the communication circuit 52 (S4). The determination model 57 is constructed based on training data including feature values calculated under conditions in which abnormalities in the molten shape occur and processing states in conditions in which the abnormalities in the molten shape occur.
　以上の判定装置５０によると、上述した判定方法を実行して、重ね合わせ溶接のためのレーザ加工における加工状態を詳細に判定することができる。 According to the determination device 50 described above, it is possible to perform the determination method described above and determine the processing state in laser processing for lap welding in detail.
　（他の実施形態）
　以上のように、本出願において開示する技術の例示として、上記の実施の形態を説明した。しかしながら、本開示における技術は、これに限定されず、適宜、変更、置き換え、付加、省略などを行った実施の形態にも適用可能である。また、上記の各実施の形態で説明した各構成要素を組み合わせて、新たな実施の形態とすることも可能である。 (Other embodiments)
As described above, the above embodiments have been described as examples of the technology disclosed in the present application. However, the technology in the present disclosure is not limited to this, and can be applied to embodiments in which modifications, replacements, additions, omissions, etc. are made as appropriate. Also, it is possible to combine the components described in each of the above embodiments to form a new embodiment.
　上記の実施形態１では、判定装置５０は、判定処理において、信号強度及びピーク強度値の特徴量を算出した（図５のＳ２）。本実施形態では、ステップＳ２において、ピーク強度値を特に算出せず、信号強度のみが特徴量として用いられてもよい。 In the first embodiment described above, the determination device 50 calculated the feature amounts of the signal intensity and the peak intensity value in the determination process (S2 in FIG. 5). In this embodiment, in step S2, only the signal intensity may be used as the feature amount without calculating the peak intensity value.
　上記の実施形態１では、判定装置５０は、分光装置４０の光センサ２２で検知された熱放射、可視光及び反射光に対応する信号を取得した（Ｓ１）。本実施形態では、判定装置５０は、熱放射、可視光及び反射光のうち１つまたは２つのみについて信号を取得してもよい。この場合、ステップＳ２～Ｓ３では、熱放射、可視光及び反射光のうち１つまたは２つのみの信号について特徴量が算出され、判定モデル５７に入力される。また、本実施形態において、判定モデル５７は、熱放射、可視光及び反射光のうち１つまたは２つのみの信号に基づく特徴量と加工状態とを訓練データとして構築されてもよい。 In the first embodiment described above, the determination device 50 acquires signals corresponding to thermal radiation, visible light, and reflected light detected by the optical sensor 22 of the spectroscopic device 40 (S1). In this embodiment, the determination device 50 may acquire signals for only one or two of thermal radiation, visible light and reflected light. In this case, in steps S 2 and S 3 , feature quantities are calculated for only one or two signals of thermal radiation, visible light, and reflected light, and input to the determination model 57 . Further, in the present embodiment, the judgment model 57 may be constructed using feature amounts and processing states based on signals of only one or two of thermal radiation, visible light, and reflected light as training data.
　上記の実施形態１では、判定モデル５７は、信号強度等の特徴量と溶融形状異常の位置、数及びサイズとを訓練データとして構築された（Ｓ１１～Ｓ１２）。本実施形態では、判定モデル５７は、特徴量と溶融形状異常の位置及び数とを訓練データとして構築されてもよい。この場合、判定装置５０は、判定処理（Ｓ１～Ｓ４）において、加工状態として溶融形状異常の位置及び数を判定する。 In the above-described Embodiment 1, the judgment model 57 is constructed using feature quantities such as signal intensity and the positions, numbers, and sizes of molten shape anomalies as training data (S11-S12). In this embodiment, the judgment model 57 may be constructed using the feature quantity and the positions and numbers of the abnormalities in the molten shape as training data. In this case, the determination device 50 determines the position and number of melt shape abnormalities as the processing state in the determination processing (S1 to S4).
　本開示における判定方法及び判定装置によると、重ね合わせ溶接のためのレーザ加工において、特に溶接領域に生じた溶融形状異常に関して、加工状態を詳細に判定することができる。 According to the determination method and determination device of the present disclosure, in laser processing for lap welding, the processing state can be determined in detail, particularly with regard to the melt shape abnormality that has occurred in the welding region.
　本開示は上述した実施形態に限定されるものではなく、種々の変更が可能である。すなわち、当業者が適宜変更した技術的手段を組み合わせて得られる実施形態についても本開示の範疇である。 The present disclosure is not limited to the above-described embodiments, and various modifications are possible. That is, embodiments obtained by combining technical means appropriately modified by those skilled in the art are also within the scope of the present disclosure.
　本開示は、重ね合わせ溶接のためのレーザ加工における加工状態の判定システムに適用可能であり、特に溶接部の溶融形状異常を判定する方法及び装置に適用可能である。 The present disclosure is applicable to a processing state determination system in laser processing for lap welding, and is particularly applicable to a method and apparatus for determining molten shape anomalies in welds.
　１　レーザ発振器
　２　レーザ伝送用ファイバ
　３　鏡筒
　４　コリメートレンズ
　５、１１　集光レンズ
　６　レーザ光
　７　第１ミラー
　８　第２ミラー
　１３　光ファイバ
　１５　コリメートレンズ
　１６　第３ミラー
　１７　第４ミラー
　１８　第５ミラー
　１９、２０、２１　集光レンズ
　２２　光センサ
　２３　伝送ケーブル
　２４　コントローラ
　２６　押さえ治具
　２７　溶融部
　３０　レーザ加工装置
　４０　分光装置
　５０　判定装置
　５１　ＣＰＵ
　５２　通信回路
　５３　記憶装置
　５６　制御プログラム
　５７　判定モデル
　７０　被加工物
　７０ａ、７０ｂ　部材
　８５　穴
　１００　判定システム
　２７０　溶接領域 Reference Signs List 1 laser oscillator 2 laser transmission fiber 3 lens barrel 4 collimating lens 5, 11 condenser lens 6 laser light 7 first mirror 8 second mirror 13 optical fiber 15 collimating lens 16 third mirror 17 fourth mirror 18 fifth mirror 19 , 20, 21 condenser lens 22 optical sensor 23 transmission cable 24 controller 26 holding jig 27 fusion zone 30 laser processing device 40 spectroscopic device 50 determination device 51 CPU
52 communication circuit 53 storage device 56 control program 57 judgment model 70 workpiece 70a, 70b member 85 hole 100 judgment system 270 welding area

Claims (8)

  1. 　重ね合わせ溶接のためのレーザ加工における加工状態の判定方法であって、
    　光センサを用いて、レーザ光が被加工物に照射されることで前記被加工物の表面に形成される溶接部において発生する熱放射光、可視光及び反射光のうち、少なくとも１つを検出する工程と、
    　前記被加工物ごとの溶接時間に対応した時間区間における前記熱放射光、前記可視光及び前記反射光の前記少なくとも１つの変化を示す信号を前記光センサから取得する工程と、
    　前記加工状態を判定する判定モデルに前記信号に基づく前記信号の信号強度を含む特徴量を入力して、前記被加工物の重ね合わせ面に異物が存在する場合に生じる溶融形状異常の、溶融長と溶融幅を有する溶接領域における位置及び数を、前記加工状態として、判定する工程と、
    　判定した前記溶融形状異常の位置及び数を判定結果として出力する工程と、
    を含み、
    　前記判定モデルは、前記溶融形状異常が発生している状況下で算出された前記特徴量と前記溶融形状異常が発生している状況下での前記加工状態とを含む訓練データに基づいて構築される
    判定方法。     A method for determining a processing state in laser processing for lap welding,
    Using an optical sensor, detect at least one of thermal radiation light, visible light, and reflected light generated at a weld formed on the surface of a workpiece by irradiating the workpiece with laser light. and
    obtaining a signal from the optical sensor indicative of a change in the at least one of the thermally emitted light, the visible light and the reflected light over a time interval corresponding to a welding time for each workpiece;
    A feature quantity including the signal intensity of the signal based on the signal is input to the judgment model for judging the machining state, and the fusion length of the fusion shape abnormality that occurs when a foreign matter is present on the superimposed surface of the workpiece. and a step of determining, as the processing state, the position and number in the welded region having the width of the melt;
    a step of outputting the position and number of the determined melt shape abnormality as a determination result;
    including
    The judgment model is constructed based on training data including the feature value calculated under the condition where the abnormal shape of the melt is generated and the processing state under the condition where the abnormal shape of the melt is generated. judgment method.
  2. 　前記判定の工程は、前記信号のピークを検出し、前記加工状態としてさらに、前記溶融形状異常のサイズを判定することを含み、
    　前記出力の工程は、判定結果としてさらに、判定した前記溶融形状異常のサイズを出力することを含み、
    　前記特徴量は、前記ピークにおける前記信号の信号強度に基づく強度値を含む
    請求項１に記載の判定方法。     The step of determining includes detecting a peak of the signal and further determining a size of the melt shape anomaly as the processing state,
    The step of outputting further includes outputting the determined size of the melt shape abnormality as a determination result,
    2. The determination method according to claim 1, wherein said feature amount includes an intensity value based on signal intensity of said signal at said peak.
  3. 　前記強度値は、前記ピークの信号強度から前記ピークを除く前記信号の信号強度の平均値を減じた値が、前記ピークの発生時間について積分されることにより得られた積分値である
    請求項２に記載の判定方法。     2. The intensity value is an integral value obtained by integrating a value obtained by subtracting an average value of signal intensities of the signals excluding the peak from the signal intensity of the peak with respect to the occurrence time of the peak. Judgment method described in.
  4. 　前記判定モデルは、前記加工状態が変化する複数の条件における各条件のもとで、前記レーザ加工を行って検出された前記熱放射光、前記可視光及び前記反射光の前記少なくとも１つに基づく信号から算出された特徴量と、前記溶接領域の外観測定により判定された前記加工状態と、を関連付けた訓練データを用いた機械学習により生成される学習済みモデルを含む
    請求項１から３のいずれか一項に記載の判定方法。     The judgment model is based on at least one of the thermal radiation light, the visible light, and the reflected light detected by performing the laser processing under each of a plurality of conditions under which the processing state changes. 4. Any one of claims 1 to 3, including a learned model generated by machine learning using training data that associates the feature amount calculated from the signal with the machining state determined by the appearance measurement of the welding region. or the determination method according to item 1.
  5. 　重ね合わせ溶接のためのレーザ加工における加工状態の判定装置であって、
    　演算回路と、
    　レーザ光が被加工物に照射されることで前記被加工物の表面に形成される溶接部において発生する熱放射光、可視光及び反射光のうち、少なくとも１つを光センサにより検出して生成された信号を受け付ける通信回路と、
    を備え、
    　前記信号は、前記被加工物ごとの溶接時間に対応した時間区間における前記熱放射光、前記可視光及び前記反射光の前記少なくとも１つの変化を示す信号であり、
    　前記演算回路は、
    　前記通信回路により、前記信号を取得し、
    　前記加工状態を判定する判定モデルに前記信号に基づく前記信号の信号強度を含む特徴量を入力して、前記被加工物の重ね合わせ面に異物が存在する場合に生じる溶融形状異常の、溶融長と溶融幅を有する溶接領域における位置及び数を、前記加工状態として、判定し、
    　判定した前記溶融形状異常の位置及び数を判定結果として、前記通信回路により出力し、
    　前記判定モデルは、前記溶融形状異常が発生している状況下で算出された前記特徴量と前記溶融形状異常が発生している状況下での前記加工状態とを含む訓練データに基づいて構築される
    判定装置。     A processing state determination device in laser processing for lap welding,
    an arithmetic circuit;
    Generated by detecting at least one of thermal radiation light, visible light, and reflected light generated at a weld formed on the surface of a workpiece by irradiating the workpiece with the laser beam, using an optical sensor. a communication circuit that receives the received signal;
    with
    the signal is a signal indicative of a change in the at least one of the thermally emitted light, the visible light, and the reflected light during a time interval corresponding to a welding time for each workpiece;
    The arithmetic circuit is
    Acquiring the signal by the communication circuit;
    A feature quantity including the signal intensity of the signal based on the signal is input to the judgment model for judging the machining state, and the fusion length of the fusion shape abnormality that occurs when a foreign matter is present on the superimposed surface of the workpiece. and the position and number in the welded area having the width of the melt as the processing state,
    outputting the position and number of the determined molten shape abnormality as a determination result from the communication circuit,
    The judgment model is constructed based on training data including the feature value calculated under the condition where the abnormal shape of the melt is generated and the processing state under the condition where the abnormal shape of the melt is generated. determination device.
  6. 　前記演算回路は、
    　前記信号のピークを検出して、前記加工状態としてさらに、前記溶融形状異常のサイズを判定し、
    　判定結果としてさらに、判定した前記溶融形状異常のサイズを前記通信回路により出力し、
    　前記特徴量は、前記ピークにおける前記信号の信号強度に基づく強度値を含む
    請求項５に記載の判定装置。     The arithmetic circuit is
    detecting the peak of the signal to further determine the size of the melt shape abnormality as the processing state;
    Further, as a determination result, the determined size of the molten shape abnormality is output by the communication circuit,
    6. The determination device according to claim 5, wherein said feature quantity includes an intensity value based on signal intensity of said signal at said peak.
  7. 　前記強度値は、前記ピークの信号強度から前記ピークを除く前記信号の信号強度の平均値を減じた値が、前記ピークの発生時間について積分されることにより得られた積分値である
    請求項６に記載の判定装置。     7. The intensity value is an integral value obtained by integrating a value obtained by subtracting an average value of signal intensities of the signals excluding the peak from the signal intensity of the peak, with respect to the occurrence time of the peak. The determination device according to .
  8. 　前記判定モデルは、前記加工状態が変化する複数の条件における各条件のもとで、前記レーザ加工を行って検出された前記熱放射光、前記可視光及び前記反射光の前記少なくとも１つに基づく信号から算出された特徴量と、前記溶接領域の外観測定により判定された前記加工状態と、を関連付けた訓練データを用いた機械学習により生成される学習済みモデルを含む
    請求項５から７のいずれか一項に記載の判定装置。     The judgment model is based on at least one of the thermal radiation light, the visible light, and the reflected light detected by performing the laser processing under each of a plurality of conditions under which the processing state changes. 8. A learned model generated by machine learning using training data that associates the feature amount calculated from the signal with the machining state determined by the appearance measurement of the welding area. or the determination device according to claim 1.
PCT/JP2022/000132 2021-02-26 2022-01-05 Determination method and determination device for laser processing state WO2022181060A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202280016159.5A CN116897090A (en) 2021-02-26 2022-01-05 Laser processing state determination method and determination device
JP2023502131A JPWO2022181060A1 (en) 2021-02-26 2022-01-05
US18/233,954 US20230384282A1 (en) 2021-02-26 2023-08-15 Determination method and determination device for laser processing state

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-029936 2021-02-26
JP2021029936 2021-02-26

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/233,954 Continuation US20230384282A1 (en) 2021-02-26 2023-08-15 Determination method and determination device for laser processing state

Publications (1)

Publication Number Publication Date
WO2022181060A1 true WO2022181060A1 (en) 2022-09-01

Family

ID=83048843

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/000132 WO2022181060A1 (en) 2021-02-26 2022-01-05 Determination method and determination device for laser processing state

Country Status (4)

Country Link
US (1) US20230384282A1 (en)
JP (1) JPWO2022181060A1 (en)
CN (1) CN116897090A (en)
WO (1) WO2022181060A1 (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08215868A (en) * 1995-02-09 1996-08-27 Nissan Motor Co Ltd Method and device for monitoring welding
JPH1158046A (en) * 1997-08-07 1999-03-02 Sumitomo Heavy Ind Ltd Instrument for detecting defect in laser beam welding
WO2012000648A1 (en) * 2010-06-28 2012-01-05 Precitec Kg Method for closed-loop controlling a laser processing operation and laser material processing head using the same
WO2013171848A1 (en) * 2012-05-15 2013-11-21 トヨタ自動車株式会社 Welding method, welding device, and battery manufacturing method
US20150001196A1 (en) * 2013-07-01 2015-01-01 Electronics And Telecommunications Research Institute Apparatus and method for monitoring laser welding bead
US20170032281A1 (en) * 2015-07-29 2017-02-02 Illinois Tool Works Inc. System and Method to Facilitate Welding Software as a Service

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08215868A (en) * 1995-02-09 1996-08-27 Nissan Motor Co Ltd Method and device for monitoring welding
JPH1158046A (en) * 1997-08-07 1999-03-02 Sumitomo Heavy Ind Ltd Instrument for detecting defect in laser beam welding
WO2012000648A1 (en) * 2010-06-28 2012-01-05 Precitec Kg Method for closed-loop controlling a laser processing operation and laser material processing head using the same
WO2013171848A1 (en) * 2012-05-15 2013-11-21 トヨタ自動車株式会社 Welding method, welding device, and battery manufacturing method
US20150001196A1 (en) * 2013-07-01 2015-01-01 Electronics And Telecommunications Research Institute Apparatus and method for monitoring laser welding bead
US20170032281A1 (en) * 2015-07-29 2017-02-02 Illinois Tool Works Inc. System and Method to Facilitate Welding Software as a Service

Also Published As

Publication number Publication date
JPWO2022181060A1 (en) 2022-09-01
CN116897090A (en) 2023-10-17
US20230384282A1 (en) 2023-11-30

Similar Documents

Publication Publication Date Title
Sun et al. Sensor systems for real-time monitoring of laser weld quality
JP3227650B2 (en) Laser welding machine and laser welding condition monitoring method
JP2004066340A (en) Laser weld monitoring system and method
KR20210091789A (en) Laser Machining Process Monitoring System and Method Using Deep Convolutional Neural Network
Wu et al. Progress and perspectives of in-situ optical monitoring in laser beam welding: Sensing, characterization and modeling
JP2006247681A (en) Monitoring device for laser beam machining
US20230201956A1 (en) Method for analyzing a laser machining process, system for analyzing a laser machining process, and laser machining system comprising such a system
US20240100626A1 (en) Laser working system for performing a working process on a workpiece by means of a laser beam and method for monitoring a working process on a workpiece by means of a laser beam
JP2023514403A (en) How to Analyze Welded Connections During Laser Welding of Workpieces
US20210107096A1 (en) Laser welding quality inspection method and laser welding quality inspection apparatus
Gao et al. Detection of weld imperfection in high-power disk laser welding based on association analysis of multi-sensing features
WO2022181359A1 (en) Laser machining condition determination method and determination device
WO2022181060A1 (en) Determination method and determination device for laser processing state
JP3184962B2 (en) Laser welding detection method
KR20180091480A (en) System and Method for detecting weld defects by type
JP2017024046A (en) Laser welding monitoring device and laser welding monitoring method
WO2023218701A1 (en) Machining condition determination method and determination device
Sikström et al. Prediction of penetration in one-sided fillet welds by in-process joint gap monitoring—an experimental study
JP2010052009A (en) Abnormality sensing method of laser beam welding system
JP3385502B2 (en) Laser welding defect detection apparatus and detection method
JP4026404B2 (en) Laser welding quality monitoring method and apparatus
JP2967671B2 (en) Monitoring device for welding status
JP2008185462A (en) Method and apparatus for judging quality of screw
JP6824355B1 (en) Laser machining monitoring method and laser machining monitoring device
JP2023166927A (en) Method and device for determining laser beam machining state

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22759103

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023502131

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 202280016159.5

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22759103

Country of ref document: EP

Kind code of ref document: A1